diff --git a/UNet/.#UNet_V6_2.py b/UNet/.#UNet_V6_2.py
deleted file mode 120000
index b44a5a4fd67f9e17d6366a68e60d3bf23ec85124..0000000000000000000000000000000000000000
--- a/UNet/.#UNet_V6_2.py
+++ /dev/null
@@ -1 +0,0 @@
-yk138599@login18-x-1.hpc.itc.rwth-aachen.de.135696:1644816141
\ No newline at end of file
diff --git a/UNet/2_Train_model.sh b/UNet/2_Train_model.sh
index ba6714656b49e62844f44c8f405202f126636ecf..77deaabbb09bc91efef7c2360d7df51c38288f97 100644
--- a/UNet/2_Train_model.sh
+++ b/UNet/2_Train_model.sh
@@ -1,12 +1,12 @@
 #!/usr/local_rwth/bin/zsh
 ### Project account
-###SBATCH --account=thes1075
+#SBATCH --account=rwth0744
 
 ### Cluster Partition
 #SBATCH --partition=c18g
 
 #SBATCH -J training_model
-#SBATCH -o Sim_logs/UNet_V6_2_64_%J.log
+#SBATCH -o Sim_logs/UNet_V9_1_%J.log
  
 #SBATCH --gres=gpu:1
 #SBATCH --time=50:00:00
@@ -15,7 +15,8 @@
 #SBATCH --mem-per-gpu=16000
 module load cuda
 module load python/3.7.11
+echo "9.1 k=7 lr=1e-06"
 pip3 install --user -Iv -q torch==1.10.1
-time python3 ./UNet_V6_2.py
+time python3 ./UNet_V9_1.py
 #print GPU Information
 #$CUDA_ROOT/extras/demo_suite/deviceQuery -noprompt
diff --git a/UNet/Sim_logs/UNet_32_V9_V10_J.log b/UNet/Sim_logs/UNet_32_V9_V10_J.log
index c5e6f0cd9f906edd3713c3477a04bfdfb9d153bc..cdfaa2382e57a9c1b9e25db147a7c49c3d3d9765 100644
--- a/UNet/Sim_logs/UNet_32_V9_V10_J.log
+++ b/UNet/Sim_logs/UNet_32_V9_V10_J.log
@@ -14,57 +14,2025 @@ WARNING: You are using pip version 21.2.4; however, version 22.0.3 is available.
 You should consider upgrading via the '/usr/local_rwth/sw/python/3.7.11/x86_64/bin/python3.7 -m pip install --upgrade pip' command.
 number auf epochs: 500
 batchsize: 32
-learning rate: 1e-05
+learning rate: 1e-06
 kernel size is: 5
  seed is: 373686838
-Traceback (most recent call last):
-  File "./UNet_V9_1.py", line 247, in <module>
-    normalization = np.load(f'{path_to_rep}/UNet/Trainingsdata/Norm_min_max_32_angles.npy')
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/npyio.py", line 441, in load
-    pickle_kwargs=pickle_kwargs)
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/format.py", line 743, in read_array
-    raise ValueError("Object arrays cannot be loaded when "
-ValueError: Object arrays cannot be loaded when allow_pickle=False
-python3 ./UNet_V9_1.py  0.86s user 1.37s system 63% cpu 3.518 total
+Epoch [0], train_loss: 0.227610, val_loss: 0.256819, val_acc: 4.355319
+Epoch [1], train_loss: 0.226198, val_loss: 0.224723, val_acc: 5.331204
+Epoch [2], train_loss: 0.224849, val_loss: 0.223483, val_acc: 5.490750
+Epoch [3], train_loss: 0.223484, val_loss: 0.222029, val_acc: 5.551895
+Epoch [4], train_loss: 0.222246, val_loss: 0.220841, val_acc: 5.600525
+Epoch [5], train_loss: 0.220996, val_loss: 0.219862, val_acc: 5.634679
+Epoch [6], train_loss: 0.219805, val_loss: 0.218626, val_acc: 5.680802
+Epoch [7], train_loss: 0.218642, val_loss: 0.217650, val_acc: 5.718689
+Epoch [8], train_loss: 0.217526, val_loss: 0.216650, val_acc: 5.758020
+Epoch [9], train_loss: 0.216444, val_loss: 0.215534, val_acc: 5.800965
+Epoch [10], train_loss: 0.215367, val_loss: 0.214404, val_acc: 5.837073
+Epoch [11], train_loss: 0.214363, val_loss: 0.213494, val_acc: 5.875845
+Epoch [12], train_loss: 0.213376, val_loss: 0.212631, val_acc: 5.912039
+Epoch [13], train_loss: 0.212424, val_loss: 0.211802, val_acc: 5.942345
+Epoch [14], train_loss: 0.211494, val_loss: 0.210826, val_acc: 5.987732
+Epoch [15], train_loss: 0.210615, val_loss: 0.209721, val_acc: 6.025274
+Epoch [16], train_loss: 0.209773, val_loss: 0.208938, val_acc: 6.047435
+Epoch [17], train_loss: 0.208937, val_loss: 0.208262, val_acc: 6.066332
+Epoch [18], train_loss: 0.208161, val_loss: 0.207726, val_acc: 6.092895
+Epoch [19], train_loss: 0.207399, val_loss: 0.206972, val_acc: 6.118100
+Epoch [20], train_loss: 0.206627, val_loss: 0.205849, val_acc: 6.155823
+Epoch [21], train_loss: 0.205930, val_loss: 0.205911, val_acc: 6.142911
+Epoch [22], train_loss: 0.205244, val_loss: 0.205217, val_acc: 6.166022
+Epoch [23], train_loss: 0.204582, val_loss: 0.204059, val_acc: 6.210975
+Epoch [24], train_loss: 0.203921, val_loss: 0.203773, val_acc: 6.216152
+Epoch [25], train_loss: 0.203281, val_loss: 0.203354, val_acc: 6.229993
+Epoch [26], train_loss: 0.202665, val_loss: 0.202323, val_acc: 6.271536
+Epoch [27], train_loss: 0.202057, val_loss: 0.202280, val_acc: 6.262787
+Epoch [28], train_loss: 0.201455, val_loss: 0.201240, val_acc: 6.298029
+Epoch [29], train_loss: 0.200905, val_loss: 0.200529, val_acc: 6.326090
+Epoch [30], train_loss: 0.200339, val_loss: 0.200443, val_acc: 6.327115
+Epoch [31], train_loss: 0.199742, val_loss: 0.199135, val_acc: 6.378264
+Epoch [32], train_loss: 0.199177, val_loss: 0.199262, val_acc: 6.365089
+Epoch [33], train_loss: 0.198637, val_loss: 0.198111, val_acc: 6.409178
+Epoch [34], train_loss: 0.198117, val_loss: 0.198649, val_acc: 6.380072
+Epoch [35], train_loss: 0.197612, val_loss: 0.198090, val_acc: 6.405452
+Epoch [36], train_loss: 0.197045, val_loss: 0.197246, val_acc: 6.436645
+Epoch [37], train_loss: 0.196551, val_loss: 0.196863, val_acc: 6.446461
+Epoch [38], train_loss: 0.196001, val_loss: 0.196515, val_acc: 6.452632
+Epoch [39], train_loss: 0.195486, val_loss: 0.195185, val_acc: 6.518932
+Epoch [40], train_loss: 0.194936, val_loss: 0.195115, val_acc: 6.513679
+Epoch [41], train_loss: 0.194408, val_loss: 0.194740, val_acc: 6.535965
+Epoch [42], train_loss: 0.193857, val_loss: 0.194403, val_acc: 6.538282
+Epoch [43], train_loss: 0.193318, val_loss: 0.193100, val_acc: 6.603024
+Epoch [44], train_loss: 0.192770, val_loss: 0.192407, val_acc: 6.628159
+Epoch [45], train_loss: 0.192243, val_loss: 0.192742, val_acc: 6.609581
+Epoch [46], train_loss: 0.191689, val_loss: 0.192097, val_acc: 6.635989
+Epoch [47], train_loss: 0.191154, val_loss: 0.190009, val_acc: 6.725545
+Epoch [48], train_loss: 0.190628, val_loss: 0.191207, val_acc: 6.665430
+Epoch [49], train_loss: 0.190118, val_loss: 0.190357, val_acc: 6.704100
+Epoch [50], train_loss: 0.189603, val_loss: 0.189958, val_acc: 6.730117
+Epoch [51], train_loss: 0.189086, val_loss: 0.189364, val_acc: 6.768140
+Epoch [52], train_loss: 0.188561, val_loss: 0.189724, val_acc: 6.745926
+Epoch [53], train_loss: 0.188001, val_loss: 0.188232, val_acc: 6.828753
+Epoch [54], train_loss: 0.187511, val_loss: 0.188055, val_acc: 6.833879
+Epoch [55], train_loss: 0.186942, val_loss: 0.187819, val_acc: 6.842078
+Epoch [56], train_loss: 0.186430, val_loss: 0.187267, val_acc: 6.881024
+Epoch [57], train_loss: 0.185876, val_loss: 0.185902, val_acc: 6.952988
+Epoch [58], train_loss: 0.185341, val_loss: 0.185635, val_acc: 6.983489
+Epoch [59], train_loss: 0.184790, val_loss: 0.185600, val_acc: 6.997245
+Epoch [60], train_loss: 0.184272, val_loss: 0.185169, val_acc: 7.033418
+Epoch [61], train_loss: 0.183710, val_loss: 0.183782, val_acc: 7.111004
+Epoch [62], train_loss: 0.183154, val_loss: 0.183323, val_acc: 7.146577
+Epoch [63], train_loss: 0.182613, val_loss: 0.182297, val_acc: 7.214869
+Epoch [64], train_loss: 0.182043, val_loss: 0.184882, val_acc: 7.096990
+Epoch [65], train_loss: 0.181515, val_loss: 0.182223, val_acc: 7.271443
+Epoch [66], train_loss: 0.180961, val_loss: 0.181961, val_acc: 7.280923
+Epoch [67], train_loss: 0.180392, val_loss: 0.181081, val_acc: 7.359409
+Epoch [68], train_loss: 0.179840, val_loss: 0.180734, val_acc: 7.390409
+Epoch [69], train_loss: 0.179297, val_loss: 0.180275, val_acc: 7.440976
+Epoch [70], train_loss: 0.178736, val_loss: 0.179827, val_acc: 7.492762
+Epoch [71], train_loss: 0.178230, val_loss: 0.178934, val_acc: 7.560650
+Epoch [72], train_loss: 0.177668, val_loss: 0.178375, val_acc: 7.617845
+Epoch [73], train_loss: 0.177127, val_loss: 0.177806, val_acc: 7.688752
+Epoch [74], train_loss: 0.176581, val_loss: 0.176626, val_acc: 7.751860
+Epoch [75], train_loss: 0.176057, val_loss: 0.176104, val_acc: 7.818749
+Epoch [76], train_loss: 0.175530, val_loss: 0.175362, val_acc: 7.877375
+Epoch [77], train_loss: 0.174990, val_loss: 0.175895, val_acc: 7.898661
+Epoch [78], train_loss: 0.174470, val_loss: 0.175946, val_acc: 7.893846
+Epoch [79], train_loss: 0.173933, val_loss: 0.173402, val_acc: 8.069204
+Epoch [80], train_loss: 0.173393, val_loss: 0.173776, val_acc: 8.072682
+Epoch [81], train_loss: 0.172878, val_loss: 0.173927, val_acc: 8.097710
+Epoch [82], train_loss: 0.172365, val_loss: 0.173838, val_acc: 8.111130
+Epoch [83], train_loss: 0.171845, val_loss: 0.172183, val_acc: 8.270483
+Epoch [84], train_loss: 0.171284, val_loss: 0.172821, val_acc: 8.244482
+Epoch [85], train_loss: 0.170764, val_loss: 0.171468, val_acc: 8.345257
+Epoch [86], train_loss: 0.170239, val_loss: 0.170790, val_acc: 8.445687
+Epoch [87], train_loss: 0.169710, val_loss: 0.170349, val_acc: 8.500198
+Epoch [88], train_loss: 0.169172, val_loss: 0.169862, val_acc: 8.571683
+Epoch [89], train_loss: 0.168653, val_loss: 0.169099, val_acc: 8.648546
+Epoch [90], train_loss: 0.168112, val_loss: 0.169124, val_acc: 8.652841
+Epoch [91], train_loss: 0.167564, val_loss: 0.168350, val_acc: 8.758090
+Epoch [92], train_loss: 0.167037, val_loss: 0.167316, val_acc: 8.867459
+Epoch [93], train_loss: 0.166518, val_loss: 0.168469, val_acc: 8.831258
+Epoch [94], train_loss: 0.166001, val_loss: 0.167495, val_acc: 8.898478
+Epoch [95], train_loss: 0.165454, val_loss: 0.165375, val_acc: 9.089100
+Epoch [96], train_loss: 0.164929, val_loss: 0.165149, val_acc: 9.133799
+Epoch [97], train_loss: 0.164447, val_loss: 0.165014, val_acc: 9.172922
+Epoch [98], train_loss: 0.163913, val_loss: 0.165548, val_acc: 9.186137
+Epoch [99], train_loss: 0.163413, val_loss: 0.164879, val_acc: 9.247452
+Epoch [100], train_loss: 0.162939, val_loss: 0.164430, val_acc: 9.301769
+Epoch [101], train_loss: 0.162468, val_loss: 0.163680, val_acc: 9.403399
+Epoch [102], train_loss: 0.161985, val_loss: 0.162778, val_acc: 9.505641
+Epoch [103], train_loss: 0.161538, val_loss: 0.162001, val_acc: 9.567216
+Epoch [104], train_loss: 0.161074, val_loss: 0.160876, val_acc: 9.654387
+Epoch [105], train_loss: 0.160629, val_loss: 0.162344, val_acc: 9.612733
+Epoch [106], train_loss: 0.160197, val_loss: 0.160529, val_acc: 9.749587
+Epoch [107], train_loss: 0.159797, val_loss: 0.161650, val_acc: 9.720076
+Epoch [108], train_loss: 0.159324, val_loss: 0.159974, val_acc: 9.820820
+Epoch [109], train_loss: 0.158904, val_loss: 0.159718, val_acc: 9.908344
+Epoch [110], train_loss: 0.158562, val_loss: 0.159693, val_acc: 9.955998
+Epoch [111], train_loss: 0.158160, val_loss: 0.159675, val_acc: 9.960833
+Epoch [112], train_loss: 0.157751, val_loss: 0.159476, val_acc: 10.003444
+Epoch [113], train_loss: 0.157378, val_loss: 0.158020, val_acc: 10.116930
+Epoch [114], train_loss: 0.157033, val_loss: 0.156712, val_acc: 10.221363
+Epoch [115], train_loss: 0.156595, val_loss: 0.157883, val_acc: 10.173634
+Epoch [116], train_loss: 0.156221, val_loss: 0.157594, val_acc: 10.255745
+Epoch [117], train_loss: 0.155859, val_loss: 0.158418, val_acc: 10.211624
+Epoch [118], train_loss: 0.155499, val_loss: 0.157731, val_acc: 10.285380
+Epoch [119], train_loss: 0.155140, val_loss: 0.155826, val_acc: 10.457133
+Epoch [120], train_loss: 0.154810, val_loss: 0.155761, val_acc: 10.472382
+Epoch [121], train_loss: 0.154441, val_loss: 0.155424, val_acc: 10.529118
+Epoch [122], train_loss: 0.154122, val_loss: 0.156436, val_acc: 10.478377
+Epoch [123], train_loss: 0.153771, val_loss: 0.155490, val_acc: 10.533587
+Epoch [124], train_loss: 0.153437, val_loss: 0.154550, val_acc: 10.646478
+Epoch [125], train_loss: 0.153048, val_loss: 0.153569, val_acc: 10.736717
+Epoch [126], train_loss: 0.152730, val_loss: 0.152710, val_acc: 10.839215
+Epoch [127], train_loss: 0.152415, val_loss: 0.153814, val_acc: 10.779072
+Epoch [128], train_loss: 0.152105, val_loss: 0.154548, val_acc: 10.752930
+Epoch [129], train_loss: 0.151776, val_loss: 0.153544, val_acc: 10.877334
+Epoch [130], train_loss: 0.151435, val_loss: 0.153504, val_acc: 10.894132
+Epoch [131], train_loss: 0.151132, val_loss: 0.152407, val_acc: 10.984577
+Epoch [132], train_loss: 0.150809, val_loss: 0.152485, val_acc: 10.992414
+Epoch [133], train_loss: 0.150507, val_loss: 0.151739, val_acc: 11.056885
+Epoch [134], train_loss: 0.150210, val_loss: 0.152010, val_acc: 11.079807
+Epoch [135], train_loss: 0.149891, val_loss: 0.151659, val_acc: 11.128430
+Epoch [136], train_loss: 0.149608, val_loss: 0.151958, val_acc: 11.129356
+Epoch [137], train_loss: 0.149308, val_loss: 0.151304, val_acc: 11.208597
+Epoch [138], train_loss: 0.148991, val_loss: 0.149842, val_acc: 11.313989
+Epoch [139], train_loss: 0.148706, val_loss: 0.149623, val_acc: 11.374372
+Epoch [140], train_loss: 0.148437, val_loss: 0.150460, val_acc: 11.384677
+Epoch [141], train_loss: 0.148122, val_loss: 0.149433, val_acc: 11.439933
+Epoch [142], train_loss: 0.147831, val_loss: 0.148930, val_acc: 11.494209
+Epoch [143], train_loss: 0.147559, val_loss: 0.147501, val_acc: 11.617744
+Epoch [144], train_loss: 0.147274, val_loss: 0.148707, val_acc: 11.528086
+Epoch [145], train_loss: 0.147005, val_loss: 0.148650, val_acc: 11.563831
+Epoch [146], train_loss: 0.146713, val_loss: 0.148185, val_acc: 11.663876
+Epoch [147], train_loss: 0.146457, val_loss: 0.149152, val_acc: 11.593708
+Epoch [148], train_loss: 0.146178, val_loss: 0.146476, val_acc: 11.818043
+Epoch [149], train_loss: 0.145929, val_loss: 0.147574, val_acc: 11.787142
+Epoch [150], train_loss: 0.145601, val_loss: 0.145771, val_acc: 11.901958
+Epoch [151], train_loss: 0.145359, val_loss: 0.146138, val_acc: 11.910983
+Epoch [152], train_loss: 0.145095, val_loss: 0.145865, val_acc: 11.929287
+Epoch [153], train_loss: 0.144834, val_loss: 0.145980, val_acc: 11.968421
+Epoch [154], train_loss: 0.144581, val_loss: 0.145965, val_acc: 11.969495
+Epoch [155], train_loss: 0.144339, val_loss: 0.144688, val_acc: 12.071909
+Epoch [156], train_loss: 0.144098, val_loss: 0.145815, val_acc: 12.028000
+Epoch [157], train_loss: 0.143833, val_loss: 0.145222, val_acc: 12.091776
+Epoch [158], train_loss: 0.143579, val_loss: 0.145152, val_acc: 12.115852
+Epoch [159], train_loss: 0.143322, val_loss: 0.145052, val_acc: 12.148233
+Epoch [160], train_loss: 0.143084, val_loss: 0.145097, val_acc: 12.152022
+Epoch [161], train_loss: 0.142837, val_loss: 0.143026, val_acc: 12.346883
+Epoch [162], train_loss: 0.142557, val_loss: 0.144635, val_acc: 12.265927
+Epoch [163], train_loss: 0.142316, val_loss: 0.143486, val_acc: 12.365000
+Epoch [164], train_loss: 0.142058, val_loss: 0.143919, val_acc: 12.329079
+Epoch [165], train_loss: 0.141841, val_loss: 0.143813, val_acc: 12.369977
+Epoch [166], train_loss: 0.141574, val_loss: 0.143073, val_acc: 12.441296
+Epoch [167], train_loss: 0.141346, val_loss: 0.142317, val_acc: 12.486316
+Epoch [168], train_loss: 0.141077, val_loss: 0.142233, val_acc: 12.565392
+Epoch [169], train_loss: 0.140796, val_loss: 0.141587, val_acc: 12.615634
+Epoch [170], train_loss: 0.140545, val_loss: 0.142091, val_acc: 12.585939
+Epoch [171], train_loss: 0.140322, val_loss: 0.141436, val_acc: 12.685486
+Epoch [172], train_loss: 0.140057, val_loss: 0.141791, val_acc: 12.654526
+Epoch [173], train_loss: 0.139827, val_loss: 0.142206, val_acc: 12.639626
+Epoch [174], train_loss: 0.139540, val_loss: 0.140901, val_acc: 12.781619
+Epoch [175], train_loss: 0.139305, val_loss: 0.139315, val_acc: 12.886707
+Epoch [176], train_loss: 0.139086, val_loss: 0.139940, val_acc: 12.858660
+Epoch [177], train_loss: 0.138846, val_loss: 0.138429, val_acc: 13.028749
+Epoch [178], train_loss: 0.138648, val_loss: 0.139366, val_acc: 12.939656
+Epoch [179], train_loss: 0.138413, val_loss: 0.139976, val_acc: 12.895535
+Epoch [180], train_loss: 0.138184, val_loss: 0.140175, val_acc: 12.914804
+Epoch [181], train_loss: 0.137988, val_loss: 0.140050, val_acc: 12.950711
+Epoch [182], train_loss: 0.137754, val_loss: 0.137957, val_acc: 13.102345
+Epoch [183], train_loss: 0.137583, val_loss: 0.139030, val_acc: 13.074813
+Epoch [184], train_loss: 0.137353, val_loss: 0.137397, val_acc: 13.175312
+Epoch [185], train_loss: 0.137182, val_loss: 0.138171, val_acc: 13.154070
+Epoch [186], train_loss: 0.136925, val_loss: 0.137553, val_acc: 13.211525
+Epoch [187], train_loss: 0.136740, val_loss: 0.136940, val_acc: 13.275466
+Epoch [188], train_loss: 0.136577, val_loss: 0.138304, val_acc: 13.176235
+Epoch [189], train_loss: 0.136298, val_loss: 0.135371, val_acc: 13.400066
+Epoch [190], train_loss: 0.136127, val_loss: 0.137752, val_acc: 13.249874
+Epoch [191], train_loss: 0.135967, val_loss: 0.138141, val_acc: 13.246906
+Epoch [192], train_loss: 0.135776, val_loss: 0.136707, val_acc: 13.355679
+Epoch [193], train_loss: 0.135572, val_loss: 0.135410, val_acc: 13.466647
+Epoch [194], train_loss: 0.135410, val_loss: 0.136623, val_acc: 13.389233
+Epoch [195], train_loss: 0.135191, val_loss: 0.136823, val_acc: 13.372538
+Epoch [196], train_loss: 0.135045, val_loss: 0.136072, val_acc: 13.443967
+Epoch [197], train_loss: 0.134805, val_loss: 0.134774, val_acc: 13.560355
+Epoch [198], train_loss: 0.134675, val_loss: 0.136122, val_acc: 13.487073
+Epoch [199], train_loss: 0.134431, val_loss: 0.134455, val_acc: 13.576872
+Epoch [200], train_loss: 0.134285, val_loss: 0.135549, val_acc: 13.550121
+Epoch [201], train_loss: 0.134104, val_loss: 0.135135, val_acc: 13.577595
+Epoch [202], train_loss: 0.133898, val_loss: 0.135652, val_acc: 13.541193
+Epoch [203], train_loss: 0.133720, val_loss: 0.134485, val_acc: 13.659431
+Epoch [204], train_loss: 0.133546, val_loss: 0.134566, val_acc: 13.660540
+Epoch [205], train_loss: 0.133381, val_loss: 0.135327, val_acc: 13.627134
+Epoch [206], train_loss: 0.133190, val_loss: 0.134511, val_acc: 13.690844
+Epoch [207], train_loss: 0.133068, val_loss: 0.134049, val_acc: 13.725305
+Epoch [208], train_loss: 0.132872, val_loss: 0.135957, val_acc: 13.574872
+Epoch [209], train_loss: 0.132692, val_loss: 0.134358, val_acc: 13.737452
+Epoch [210], train_loss: 0.132521, val_loss: 0.133295, val_acc: 13.860023
+Epoch [211], train_loss: 0.132334, val_loss: 0.133920, val_acc: 13.831337
+Epoch [212], train_loss: 0.132184, val_loss: 0.133823, val_acc: 13.817361
+Epoch [213], train_loss: 0.131980, val_loss: 0.132919, val_acc: 13.913481
+Epoch [214], train_loss: 0.131859, val_loss: 0.134401, val_acc: 13.813931
+Epoch [215], train_loss: 0.131682, val_loss: 0.132714, val_acc: 13.933662
+Epoch [216], train_loss: 0.131506, val_loss: 0.132398, val_acc: 13.963894
+Epoch [217], train_loss: 0.131335, val_loss: 0.133397, val_acc: 13.896288
+Epoch [218], train_loss: 0.131190, val_loss: 0.132089, val_acc: 14.023612
+Epoch [219], train_loss: 0.131004, val_loss: 0.131430, val_acc: 14.083266
+Epoch [220], train_loss: 0.130860, val_loss: 0.132223, val_acc: 14.031086
+Epoch [221], train_loss: 0.130716, val_loss: 0.131939, val_acc: 14.041862
+Epoch [222], train_loss: 0.130575, val_loss: 0.132550, val_acc: 14.033080
+Epoch [223], train_loss: 0.130392, val_loss: 0.132641, val_acc: 14.048969
+Epoch [224], train_loss: 0.130228, val_loss: 0.130955, val_acc: 14.177105
+Epoch [225], train_loss: 0.130059, val_loss: 0.130871, val_acc: 14.207293
+Epoch [226], train_loss: 0.129964, val_loss: 0.130383, val_acc: 14.212212
+Epoch [227], train_loss: 0.129760, val_loss: 0.131432, val_acc: 14.161558
+Epoch [228], train_loss: 0.129626, val_loss: 0.129508, val_acc: 14.314246
+Epoch [229], train_loss: 0.129479, val_loss: 0.130530, val_acc: 14.267905
+Epoch [230], train_loss: 0.129309, val_loss: 0.130590, val_acc: 14.282993
+Epoch [231], train_loss: 0.129139, val_loss: 0.130266, val_acc: 14.268251
+Epoch [232], train_loss: 0.128992, val_loss: 0.129821, val_acc: 14.339046
+Epoch [233], train_loss: 0.128847, val_loss: 0.129863, val_acc: 14.308224
+Epoch [234], train_loss: 0.128672, val_loss: 0.130221, val_acc: 14.298942
+Epoch [235], train_loss: 0.128531, val_loss: 0.129508, val_acc: 14.367423
+Epoch [236], train_loss: 0.128372, val_loss: 0.129429, val_acc: 14.402047
+Epoch [237], train_loss: 0.128232, val_loss: 0.128357, val_acc: 14.475517
+Epoch [238], train_loss: 0.128104, val_loss: 0.128972, val_acc: 14.430723
+Epoch [239], train_loss: 0.127948, val_loss: 0.128175, val_acc: 14.549207
+Epoch [240], train_loss: 0.127828, val_loss: 0.131154, val_acc: 14.217744
+Epoch [241], train_loss: 0.127643, val_loss: 0.127905, val_acc: 14.605879
+Epoch [242], train_loss: 0.127498, val_loss: 0.128753, val_acc: 14.513625
+Epoch [243], train_loss: 0.127383, val_loss: 0.127357, val_acc: 14.640419
+Epoch [244], train_loss: 0.127225, val_loss: 0.128469, val_acc: 14.557202
+Epoch [245], train_loss: 0.127091, val_loss: 0.127789, val_acc: 14.623334
+Epoch [246], train_loss: 0.126921, val_loss: 0.128138, val_acc: 14.572148
+Epoch [247], train_loss: 0.126784, val_loss: 0.128274, val_acc: 14.592034
+Epoch [248], train_loss: 0.126654, val_loss: 0.126016, val_acc: 14.811917
+Epoch [249], train_loss: 0.126481, val_loss: 0.127562, val_acc: 14.679796
+Epoch [250], train_loss: 0.126365, val_loss: 0.126800, val_acc: 14.724627
+Epoch [251], train_loss: 0.126237, val_loss: 0.127608, val_acc: 14.681744
+Epoch [252], train_loss: 0.126078, val_loss: 0.127883, val_acc: 14.685838
+Epoch [253], train_loss: 0.125936, val_loss: 0.126988, val_acc: 14.704013
+Epoch [254], train_loss: 0.125807, val_loss: 0.128096, val_acc: 14.702049
+Epoch [255], train_loss: 0.125639, val_loss: 0.126733, val_acc: 14.802374
+Epoch [256], train_loss: 0.125522, val_loss: 0.127643, val_acc: 14.771879
+Epoch [257], train_loss: 0.125378, val_loss: 0.127725, val_acc: 14.753353
+Epoch [258], train_loss: 0.125274, val_loss: 0.127540, val_acc: 14.727517
+Epoch [259], train_loss: 0.125116, val_loss: 0.126191, val_acc: 14.885668
+Epoch [260], train_loss: 0.124971, val_loss: 0.125710, val_acc: 14.920226
+Epoch [261], train_loss: 0.124832, val_loss: 0.125375, val_acc: 14.967013
+Epoch [262], train_loss: 0.124670, val_loss: 0.125952, val_acc: 14.921576
+Epoch [263], train_loss: 0.124589, val_loss: 0.126231, val_acc: 14.927463
+Epoch [264], train_loss: 0.124442, val_loss: 0.126495, val_acc: 14.926120
+Epoch [265], train_loss: 0.124280, val_loss: 0.125044, val_acc: 15.035172
+Epoch [266], train_loss: 0.124173, val_loss: 0.125766, val_acc: 14.985662
+Epoch [267], train_loss: 0.124032, val_loss: 0.124185, val_acc: 15.113519
+Epoch [268], train_loss: 0.123899, val_loss: 0.124748, val_acc: 15.001130
+Epoch [269], train_loss: 0.123783, val_loss: 0.124968, val_acc: 15.061253
+Epoch [270], train_loss: 0.123693, val_loss: 0.125218, val_acc: 15.038279
+Epoch [271], train_loss: 0.123509, val_loss: 0.124959, val_acc: 15.079530
+Epoch [272], train_loss: 0.123404, val_loss: 0.125281, val_acc: 15.079861
+Epoch [273], train_loss: 0.123294, val_loss: 0.125705, val_acc: 15.017892
+Epoch [274], train_loss: 0.123178, val_loss: 0.125349, val_acc: 15.050595
+Epoch [275], train_loss: 0.123029, val_loss: 0.124609, val_acc: 15.188061
+Epoch [276], train_loss: 0.122914, val_loss: 0.123697, val_acc: 15.191736
+Epoch [277], train_loss: 0.122742, val_loss: 0.122789, val_acc: 15.379465
+Epoch [278], train_loss: 0.122637, val_loss: 0.124124, val_acc: 15.186746
+Epoch [279], train_loss: 0.122525, val_loss: 0.123281, val_acc: 15.330956
+Epoch [280], train_loss: 0.122399, val_loss: 0.122771, val_acc: 15.369238
+Epoch [281], train_loss: 0.122272, val_loss: 0.124374, val_acc: 15.169448
+Epoch [282], train_loss: 0.122118, val_loss: 0.122546, val_acc: 15.338708
+Epoch [283], train_loss: 0.121961, val_loss: 0.122335, val_acc: 15.375583
+Epoch [284], train_loss: 0.121854, val_loss: 0.121782, val_acc: 15.482336
+Epoch [285], train_loss: 0.121733, val_loss: 0.123143, val_acc: 15.389874
+Epoch [286], train_loss: 0.121606, val_loss: 0.123555, val_acc: 15.347246
+Epoch [287], train_loss: 0.121521, val_loss: 0.122810, val_acc: 15.399924
+Epoch [288], train_loss: 0.121370, val_loss: 0.122939, val_acc: 15.465427
+Epoch [289], train_loss: 0.121250, val_loss: 0.121889, val_acc: 15.453508
+Epoch [290], train_loss: 0.121110, val_loss: 0.122427, val_acc: 15.429498
+Epoch [291], train_loss: 0.121025, val_loss: 0.122578, val_acc: 15.423821
+Epoch [292], train_loss: 0.120890, val_loss: 0.122198, val_acc: 15.426298
+Epoch [293], train_loss: 0.120771, val_loss: 0.121980, val_acc: 15.500494
+Epoch [294], train_loss: 0.120620, val_loss: 0.122334, val_acc: 15.472884
+Epoch [295], train_loss: 0.120489, val_loss: 0.121980, val_acc: 15.549141
+Epoch [296], train_loss: 0.120417, val_loss: 0.122119, val_acc: 15.530356
+Epoch [297], train_loss: 0.120274, val_loss: 0.121588, val_acc: 15.567421
+Epoch [298], train_loss: 0.120167, val_loss: 0.121160, val_acc: 15.645597
+Epoch [299], train_loss: 0.120044, val_loss: 0.121760, val_acc: 15.578276
+Epoch [300], train_loss: 0.119933, val_loss: 0.121570, val_acc: 15.610322
+Epoch [301], train_loss: 0.119785, val_loss: 0.121463, val_acc: 15.612547
+Epoch [302], train_loss: 0.119705, val_loss: 0.120589, val_acc: 15.742451
+Epoch [303], train_loss: 0.119571, val_loss: 0.120632, val_acc: 15.723878
+Epoch [304], train_loss: 0.119449, val_loss: 0.120907, val_acc: 15.684986
+Epoch [305], train_loss: 0.119369, val_loss: 0.119795, val_acc: 15.752221
+Epoch [306], train_loss: 0.119243, val_loss: 0.121582, val_acc: 15.607382
+Epoch [307], train_loss: 0.119089, val_loss: 0.121054, val_acc: 15.732404
+Epoch [308], train_loss: 0.119011, val_loss: 0.121624, val_acc: 15.620827
+Epoch [309], train_loss: 0.118872, val_loss: 0.119247, val_acc: 15.874813
+Epoch [310], train_loss: 0.118763, val_loss: 0.119579, val_acc: 15.830860
+Epoch [311], train_loss: 0.118623, val_loss: 0.119677, val_acc: 15.825933
+Epoch [312], train_loss: 0.118501, val_loss: 0.118006, val_acc: 16.064877
+Epoch [313], train_loss: 0.118416, val_loss: 0.120510, val_acc: 15.743061
+Epoch [314], train_loss: 0.118306, val_loss: 0.119209, val_acc: 15.913227
+Epoch [315], train_loss: 0.118166, val_loss: 0.118444, val_acc: 16.058268
+Epoch [316], train_loss: 0.118080, val_loss: 0.119429, val_acc: 15.877677
+Epoch [317], train_loss: 0.117944, val_loss: 0.120091, val_acc: 15.887933
+Epoch [318], train_loss: 0.117855, val_loss: 0.118838, val_acc: 15.914166
+Epoch [319], train_loss: 0.117726, val_loss: 0.119868, val_acc: 15.822665
+Epoch [320], train_loss: 0.117609, val_loss: 0.117865, val_acc: 16.035093
+Epoch [321], train_loss: 0.117508, val_loss: 0.118670, val_acc: 16.022758
+Epoch [322], train_loss: 0.117393, val_loss: 0.118414, val_acc: 16.019794
+Epoch [323], train_loss: 0.117300, val_loss: 0.117919, val_acc: 16.084503
+Epoch [324], train_loss: 0.117142, val_loss: 0.119465, val_acc: 15.932932
+Epoch [325], train_loss: 0.117061, val_loss: 0.116263, val_acc: 16.273550
+Epoch [326], train_loss: 0.116929, val_loss: 0.117224, val_acc: 16.198818
+Epoch [327], train_loss: 0.116849, val_loss: 0.117831, val_acc: 16.143253
+Epoch [328], train_loss: 0.116744, val_loss: 0.117389, val_acc: 16.152470
+Epoch [329], train_loss: 0.116611, val_loss: 0.119102, val_acc: 16.016827
+Epoch [330], train_loss: 0.116517, val_loss: 0.117461, val_acc: 16.204895
+Epoch [331], train_loss: 0.116401, val_loss: 0.116874, val_acc: 16.260973
+Epoch [332], train_loss: 0.116266, val_loss: 0.117713, val_acc: 16.209833
+Epoch [333], train_loss: 0.116226, val_loss: 0.118170, val_acc: 16.159573
+Epoch [334], train_loss: 0.116087, val_loss: 0.117799, val_acc: 16.179205
+Epoch [335], train_loss: 0.115959, val_loss: 0.116644, val_acc: 16.327051
+Epoch [336], train_loss: 0.115868, val_loss: 0.117261, val_acc: 16.228107
+Epoch [337], train_loss: 0.115748, val_loss: 0.117576, val_acc: 16.246561
+Epoch [338], train_loss: 0.115617, val_loss: 0.116578, val_acc: 16.315481
+Epoch [339], train_loss: 0.115508, val_loss: 0.116925, val_acc: 16.277622
+Epoch [340], train_loss: 0.115449, val_loss: 0.116958, val_acc: 16.305717
+Epoch [341], train_loss: 0.115338, val_loss: 0.116791, val_acc: 16.323721
+Epoch [342], train_loss: 0.115223, val_loss: 0.116919, val_acc: 16.381731
+Epoch [343], train_loss: 0.115122, val_loss: 0.115896, val_acc: 16.417248
+Epoch [344], train_loss: 0.115023, val_loss: 0.116159, val_acc: 16.440744
+Epoch [345], train_loss: 0.114894, val_loss: 0.116059, val_acc: 16.451687
+Epoch [346], train_loss: 0.114809, val_loss: 0.114675, val_acc: 16.574768
+Epoch [347], train_loss: 0.114702, val_loss: 0.115233, val_acc: 16.497250
+Epoch [348], train_loss: 0.114575, val_loss: 0.116562, val_acc: 16.394260
+Epoch [349], train_loss: 0.114515, val_loss: 0.115976, val_acc: 16.461452
+Epoch [350], train_loss: 0.114406, val_loss: 0.115751, val_acc: 16.465967
+Epoch [351], train_loss: 0.114262, val_loss: 0.115112, val_acc: 16.586782
+Epoch [352], train_loss: 0.114213, val_loss: 0.115443, val_acc: 16.500351
+Epoch [353], train_loss: 0.114085, val_loss: 0.114825, val_acc: 16.565659
+Epoch [354], train_loss: 0.113993, val_loss: 0.114765, val_acc: 16.609478
+Epoch [355], train_loss: 0.113873, val_loss: 0.114419, val_acc: 16.618572
+Epoch [356], train_loss: 0.113782, val_loss: 0.113709, val_acc: 16.694412
+Epoch [357], train_loss: 0.113695, val_loss: 0.113917, val_acc: 16.737686
+Epoch [358], train_loss: 0.113556, val_loss: 0.114271, val_acc: 16.666834
+Epoch [359], train_loss: 0.113485, val_loss: 0.114312, val_acc: 16.694735
+Epoch [360], train_loss: 0.113332, val_loss: 0.115106, val_acc: 16.661507
+Epoch [361], train_loss: 0.113294, val_loss: 0.115194, val_acc: 16.563011
+Epoch [362], train_loss: 0.113190, val_loss: 0.114107, val_acc: 16.729103
+Epoch [363], train_loss: 0.113087, val_loss: 0.114965, val_acc: 16.616140
+Epoch [364], train_loss: 0.112926, val_loss: 0.114340, val_acc: 16.726357
+Epoch [365], train_loss: 0.112887, val_loss: 0.114050, val_acc: 16.693884
+Epoch [366], train_loss: 0.112752, val_loss: 0.112507, val_acc: 16.863663
+Epoch [367], train_loss: 0.112678, val_loss: 0.114341, val_acc: 16.706074
+Epoch [368], train_loss: 0.112542, val_loss: 0.113952, val_acc: 16.756378
+Epoch [369], train_loss: 0.112477, val_loss: 0.113874, val_acc: 16.746611
+Epoch [370], train_loss: 0.112358, val_loss: 0.113844, val_acc: 16.749434
+Epoch [371], train_loss: 0.112258, val_loss: 0.114374, val_acc: 16.679260
+Epoch [372], train_loss: 0.112211, val_loss: 0.112796, val_acc: 16.862690
+Epoch [373], train_loss: 0.112088, val_loss: 0.112966, val_acc: 16.889532
+Epoch [374], train_loss: 0.111975, val_loss: 0.114374, val_acc: 16.710199
+Epoch [375], train_loss: 0.111860, val_loss: 0.112359, val_acc: 16.941311
+Epoch [376], train_loss: 0.111782, val_loss: 0.112282, val_acc: 16.933262
+Epoch [377], train_loss: 0.111654, val_loss: 0.112513, val_acc: 16.906364
+Epoch [378], train_loss: 0.111591, val_loss: 0.113998, val_acc: 16.787838
+Epoch [379], train_loss: 0.111492, val_loss: 0.111522, val_acc: 17.054918
+Epoch [380], train_loss: 0.111408, val_loss: 0.113175, val_acc: 16.908665
+Epoch [381], train_loss: 0.111274, val_loss: 0.113229, val_acc: 16.890810
+Epoch [382], train_loss: 0.111188, val_loss: 0.110685, val_acc: 17.163837
+Epoch [383], train_loss: 0.111101, val_loss: 0.112493, val_acc: 16.938726
+Epoch [384], train_loss: 0.110984, val_loss: 0.110733, val_acc: 17.108549
+Epoch [385], train_loss: 0.110899, val_loss: 0.111213, val_acc: 17.065020
+Epoch [386], train_loss: 0.110779, val_loss: 0.109982, val_acc: 17.241261
+Epoch [387], train_loss: 0.110706, val_loss: 0.111217, val_acc: 17.070763
+Epoch [388], train_loss: 0.110649, val_loss: 0.112347, val_acc: 16.954473
+Epoch [389], train_loss: 0.110521, val_loss: 0.112415, val_acc: 17.015759
+Epoch [390], train_loss: 0.110401, val_loss: 0.111462, val_acc: 17.125414
+Epoch [391], train_loss: 0.110317, val_loss: 0.111690, val_acc: 17.052383
+Epoch [392], train_loss: 0.110219, val_loss: 0.110115, val_acc: 17.220579
+Epoch [393], train_loss: 0.110163, val_loss: 0.111808, val_acc: 17.082106
+Epoch [394], train_loss: 0.110022, val_loss: 0.111502, val_acc: 17.143742
+Epoch [395], train_loss: 0.109954, val_loss: 0.111153, val_acc: 17.166183
+Epoch [396], train_loss: 0.109849, val_loss: 0.110899, val_acc: 17.196285
+Epoch [397], train_loss: 0.109752, val_loss: 0.110734, val_acc: 17.190384
+Epoch [398], train_loss: 0.109673, val_loss: 0.110761, val_acc: 17.191666
+Epoch [399], train_loss: 0.109562, val_loss: 0.110852, val_acc: 17.198437
+Epoch [400], train_loss: 0.109513, val_loss: 0.111311, val_acc: 17.129711
+Epoch [401], train_loss: 0.109386, val_loss: 0.110291, val_acc: 17.238230
+Epoch [402], train_loss: 0.109329, val_loss: 0.109958, val_acc: 17.271160
+Epoch [403], train_loss: 0.109209, val_loss: 0.109622, val_acc: 17.368778
+Epoch [404], train_loss: 0.109115, val_loss: 0.109779, val_acc: 17.265915
+Epoch [405], train_loss: 0.109015, val_loss: 0.111390, val_acc: 17.100155
+Epoch [406], train_loss: 0.108954, val_loss: 0.108249, val_acc: 17.505260
+Epoch [407], train_loss: 0.108824, val_loss: 0.108797, val_acc: 17.437168
+Epoch [408], train_loss: 0.108757, val_loss: 0.109070, val_acc: 17.468109
+Epoch [409], train_loss: 0.108680, val_loss: 0.109901, val_acc: 17.308050
+Epoch [410], train_loss: 0.108567, val_loss: 0.109512, val_acc: 17.388308
+Epoch [411], train_loss: 0.108472, val_loss: 0.108525, val_acc: 17.446932
+Epoch [412], train_loss: 0.108387, val_loss: 0.111205, val_acc: 17.198576
+Epoch [413], train_loss: 0.108237, val_loss: 0.109123, val_acc: 17.419786
+Epoch [414], train_loss: 0.108227, val_loss: 0.110267, val_acc: 17.332409
+Epoch [415], train_loss: 0.108095, val_loss: 0.109573, val_acc: 17.408960
+Epoch [416], train_loss: 0.108028, val_loss: 0.110470, val_acc: 17.274391
+Epoch [417], train_loss: 0.107959, val_loss: 0.110647, val_acc: 17.347702
+Epoch [418], train_loss: 0.107845, val_loss: 0.109192, val_acc: 17.434921
+Epoch [419], train_loss: 0.107747, val_loss: 0.109405, val_acc: 17.457499
+Epoch [420], train_loss: 0.107666, val_loss: 0.109040, val_acc: 17.462378
+Epoch [421], train_loss: 0.107549, val_loss: 0.108927, val_acc: 17.457479
+Epoch [422], train_loss: 0.107523, val_loss: 0.107911, val_acc: 17.598211
+Epoch [423], train_loss: 0.107401, val_loss: 0.109224, val_acc: 17.480982
+Epoch [424], train_loss: 0.107329, val_loss: 0.108019, val_acc: 17.532421
+Epoch [425], train_loss: 0.107248, val_loss: 0.108815, val_acc: 17.509960
+Epoch [426], train_loss: 0.107153, val_loss: 0.108727, val_acc: 17.566467
+Epoch [427], train_loss: 0.107037, val_loss: 0.108997, val_acc: 17.467316
+Epoch [428], train_loss: 0.106963, val_loss: 0.109469, val_acc: 17.508879
+Epoch [429], train_loss: 0.106890, val_loss: 0.106386, val_acc: 17.848875
+Epoch [430], train_loss: 0.106801, val_loss: 0.107991, val_acc: 17.530224
+Epoch [431], train_loss: 0.106704, val_loss: 0.108590, val_acc: 17.587790
+Epoch [432], train_loss: 0.106633, val_loss: 0.107824, val_acc: 17.664507
+Epoch [433], train_loss: 0.106543, val_loss: 0.107121, val_acc: 17.746830
+Epoch [434], train_loss: 0.106418, val_loss: 0.106910, val_acc: 17.793304
+Epoch [435], train_loss: 0.106345, val_loss: 0.106589, val_acc: 17.817167
+Epoch [436], train_loss: 0.106263, val_loss: 0.106815, val_acc: 17.767788
+Epoch [437], train_loss: 0.106186, val_loss: 0.106976, val_acc: 17.749395
+Epoch [438], train_loss: 0.106109, val_loss: 0.105770, val_acc: 17.936157
+Epoch [439], train_loss: 0.106039, val_loss: 0.106736, val_acc: 17.836176
+Epoch [440], train_loss: 0.105900, val_loss: 0.105905, val_acc: 17.912085
+Epoch [441], train_loss: 0.105822, val_loss: 0.106086, val_acc: 17.870703
+Epoch [442], train_loss: 0.105778, val_loss: 0.106871, val_acc: 17.783575
+Epoch [443], train_loss: 0.105650, val_loss: 0.106410, val_acc: 17.892088
+Epoch [444], train_loss: 0.105571, val_loss: 0.108199, val_acc: 17.681612
+Epoch [445], train_loss: 0.105441, val_loss: 0.106230, val_acc: 17.933804
+Epoch [446], train_loss: 0.105333, val_loss: 0.106084, val_acc: 17.886717
+Epoch [447], train_loss: 0.105241, val_loss: 0.106298, val_acc: 17.854856
+Epoch [448], train_loss: 0.105163, val_loss: 0.107205, val_acc: 17.810083
+Epoch [449], train_loss: 0.105007, val_loss: 0.105824, val_acc: 17.912079
+Epoch [450], train_loss: 0.104908, val_loss: 0.106286, val_acc: 17.921518
+Epoch [451], train_loss: 0.104791, val_loss: 0.106901, val_acc: 17.862072
+Epoch [452], train_loss: 0.104689, val_loss: 0.107201, val_acc: 17.752670
+Epoch [453], train_loss: 0.104560, val_loss: 0.105737, val_acc: 17.928247
+Epoch [454], train_loss: 0.104447, val_loss: 0.105537, val_acc: 18.001427
+Epoch [455], train_loss: 0.104346, val_loss: 0.105729, val_acc: 18.016590
+Epoch [456], train_loss: 0.104225, val_loss: 0.104769, val_acc: 18.155117
+Epoch [457], train_loss: 0.104095, val_loss: 0.104890, val_acc: 18.118568
+Epoch [458], train_loss: 0.104030, val_loss: 0.105540, val_acc: 17.987755
+Epoch [459], train_loss: 0.103922, val_loss: 0.104177, val_acc: 18.140474
+Epoch [460], train_loss: 0.103825, val_loss: 0.104712, val_acc: 18.071985
+Epoch [461], train_loss: 0.103747, val_loss: 0.104837, val_acc: 18.101192
+Epoch [462], train_loss: 0.103671, val_loss: 0.105569, val_acc: 18.056684
+Epoch [463], train_loss: 0.103517, val_loss: 0.104548, val_acc: 18.141953
+Epoch [464], train_loss: 0.103440, val_loss: 0.105262, val_acc: 18.080280
+Epoch [465], train_loss: 0.103364, val_loss: 0.105077, val_acc: 18.122522
+Epoch [466], train_loss: 0.103263, val_loss: 0.104197, val_acc: 18.158810
+Epoch [467], train_loss: 0.103200, val_loss: 0.104892, val_acc: 18.095589
+Epoch [468], train_loss: 0.103097, val_loss: 0.102841, val_acc: 18.332382
+Epoch [469], train_loss: 0.103009, val_loss: 0.103788, val_acc: 18.217295
+Epoch [470], train_loss: 0.102945, val_loss: 0.103354, val_acc: 18.352573
+Epoch [471], train_loss: 0.102832, val_loss: 0.103689, val_acc: 18.278385
+Epoch [472], train_loss: 0.102712, val_loss: 0.103428, val_acc: 18.313944
+Epoch [473], train_loss: 0.102667, val_loss: 0.104623, val_acc: 18.201906
+Epoch [474], train_loss: 0.102595, val_loss: 0.104566, val_acc: 18.213978
+Epoch [475], train_loss: 0.102455, val_loss: 0.101728, val_acc: 18.541285
+Epoch [476], train_loss: 0.102424, val_loss: 0.102274, val_acc: 18.462336
+Epoch [477], train_loss: 0.102306, val_loss: 0.104503, val_acc: 18.231899
+Epoch [478], train_loss: 0.102180, val_loss: 0.103930, val_acc: 18.306080
+Epoch [479], train_loss: 0.102150, val_loss: 0.103697, val_acc: 18.361927
+Epoch [480], train_loss: 0.102038, val_loss: 0.102816, val_acc: 18.349003
+Epoch [481], train_loss: 0.101956, val_loss: 0.101738, val_acc: 18.543564
+Epoch [482], train_loss: 0.101909, val_loss: 0.104101, val_acc: 18.266621
+Epoch [483], train_loss: 0.101845, val_loss: 0.102896, val_acc: 18.423439
+Epoch [484], train_loss: 0.101713, val_loss: 0.102109, val_acc: 18.471848
+Epoch [485], train_loss: 0.101666, val_loss: 0.103507, val_acc: 18.314812
+Epoch [486], train_loss: 0.101614, val_loss: 0.104111, val_acc: 18.231899
+Epoch [487], train_loss: 0.101521, val_loss: 0.102856, val_acc: 18.395992
+Epoch [488], train_loss: 0.101421, val_loss: 0.102972, val_acc: 18.399666
+Epoch [489], train_loss: 0.101367, val_loss: 0.102299, val_acc: 18.440769
+Epoch [490], train_loss: 0.101228, val_loss: 0.102889, val_acc: 18.493307
+Epoch [491], train_loss: 0.101142, val_loss: 0.100611, val_acc: 18.759329
+Epoch [492], train_loss: 0.101074, val_loss: 0.102811, val_acc: 18.399933
+Epoch [493], train_loss: 0.101018, val_loss: 0.102495, val_acc: 18.492559
+Epoch [494], train_loss: 0.100968, val_loss: 0.100768, val_acc: 18.649775
+Epoch [495], train_loss: 0.100854, val_loss: 0.102008, val_acc: 18.542706
+Epoch [496], train_loss: 0.100798, val_loss: 0.102281, val_acc: 18.567795
+Epoch [497], train_loss: 0.100716, val_loss: 0.101941, val_acc: 18.568689
+Epoch [498], train_loss: 0.100604, val_loss: 0.100813, val_acc: 18.749662
+Epoch [499], train_loss: 0.100550, val_loss: 0.101894, val_acc: 18.608345
+python3 ./UNet_V9_1.py  6382.99s user 6041.10s system 99% cpu 3:27:21.68 total
 number auf epochs: 500
 batchsize: 32
-learning rate: 1e-05
+learning rate: 3e-05
 kernel size is: 7
  seed is: 373686838
-Traceback (most recent call last):
-  File "./UNet_V9_2.py", line 247, in <module>
-    normalization = np.load(f'{path_to_rep}/UNet/Trainingsdata/Norm_min_max_32_angles.npy')
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/npyio.py", line 441, in load
-    pickle_kwargs=pickle_kwargs)
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/format.py", line 743, in read_array
-    raise ValueError("Object arrays cannot be loaded when "
-ValueError: Object arrays cannot be loaded when allow_pickle=False
-python3 ./UNet_V9_2.py  0.87s user 1.33s system 79% cpu 2.786 total
+Epoch [0], train_loss: 0.196615, val_loss: 0.149808, val_acc: 7.093150
+Epoch [1], train_loss: 0.181424, val_loss: 0.174532, val_acc: 8.155859
+Epoch [2], train_loss: 0.165694, val_loss: 0.163254, val_acc: 10.056608
+Epoch [3], train_loss: 0.153604, val_loss: 0.154151, val_acc: 11.264233
+Epoch [4], train_loss: 0.145193, val_loss: 0.142645, val_acc: 12.406852
+Epoch [5], train_loss: 0.139027, val_loss: 0.138726, val_acc: 13.137707
+Epoch [6], train_loss: 0.134043, val_loss: 0.133129, val_acc: 13.367352
+Epoch [7], train_loss: 0.129563, val_loss: 0.130609, val_acc: 14.159947
+Epoch [8], train_loss: 0.125800, val_loss: 0.126323, val_acc: 14.878631
+Epoch [9], train_loss: 0.121892, val_loss: 0.120046, val_acc: 15.129633
+Epoch [10], train_loss: 0.118212, val_loss: 0.115021, val_acc: 16.044514
+Epoch [11], train_loss: 0.115016, val_loss: 0.123640, val_acc: 16.172626
+Epoch [12], train_loss: 0.112102, val_loss: 0.109974, val_acc: 17.078318
+Epoch [13], train_loss: 0.109278, val_loss: 0.107066, val_acc: 17.591438
+Epoch [14], train_loss: 0.106835, val_loss: 0.112522, val_acc: 17.526175
+Epoch [15], train_loss: 0.104322, val_loss: 0.107607, val_acc: 18.316372
+Epoch [16], train_loss: 0.101897, val_loss: 0.094917, val_acc: 19.434975
+Epoch [17], train_loss: 0.099618, val_loss: 0.112208, val_acc: 18.432539
+Epoch [18], train_loss: 0.097494, val_loss: 0.097345, val_acc: 19.728563
+Epoch [19], train_loss: 0.095597, val_loss: 0.108000, val_acc: 19.513643
+Epoch [20], train_loss: 0.093651, val_loss: 0.092653, val_acc: 20.337820
+Epoch [21], train_loss: 0.092159, val_loss: 0.089910, val_acc: 20.602448
+Epoch [22], train_loss: 0.090827, val_loss: 0.090614, val_acc: 20.189222
+Epoch [23], train_loss: 0.089199, val_loss: 0.085498, val_acc: 20.651320
+Epoch [24], train_loss: 0.088020, val_loss: 0.080348, val_acc: 21.712244
+Epoch [25], train_loss: 0.086928, val_loss: 0.078761, val_acc: 21.472775
+Epoch [26], train_loss: 0.085789, val_loss: 0.084085, val_acc: 21.515829
+Epoch [27], train_loss: 0.084461, val_loss: 0.076151, val_acc: 21.697571
+Epoch [28], train_loss: 0.083695, val_loss: 0.082897, val_acc: 21.157988
+Epoch [29], train_loss: 0.082668, val_loss: 0.081919, val_acc: 21.903126
+Epoch [30], train_loss: 0.081778, val_loss: 0.080048, val_acc: 22.038927
+Epoch [31], train_loss: 0.080658, val_loss: 0.078456, val_acc: 22.199848
+Epoch [32], train_loss: 0.080097, val_loss: 0.073984, val_acc: 22.205317
+Epoch [33], train_loss: 0.079314, val_loss: 0.078205, val_acc: 22.575281
+Epoch [34], train_loss: 0.078413, val_loss: 0.073717, val_acc: 22.325487
+Epoch [35], train_loss: 0.078019, val_loss: 0.071142, val_acc: 23.226921
+Epoch [36], train_loss: 0.077305, val_loss: 0.072603, val_acc: 22.856422
+Epoch [37], train_loss: 0.076529, val_loss: 0.073045, val_acc: 22.841948
+Epoch [38], train_loss: 0.075960, val_loss: 0.073071, val_acc: 22.751474
+Epoch [39], train_loss: 0.075217, val_loss: 0.072099, val_acc: 22.908068
+Epoch [40], train_loss: 0.074639, val_loss: 0.068175, val_acc: 23.134367
+Epoch [41], train_loss: 0.073949, val_loss: 0.072130, val_acc: 22.772558
+Epoch [42], train_loss: 0.073467, val_loss: 0.072889, val_acc: 23.033630
+Epoch [43], train_loss: 0.073222, val_loss: 0.069077, val_acc: 23.389429
+Epoch [44], train_loss: 0.072461, val_loss: 0.070175, val_acc: 23.072086
+Epoch [45], train_loss: 0.072077, val_loss: 0.070667, val_acc: 23.375322
+Epoch [46], train_loss: 0.071492, val_loss: 0.068260, val_acc: 23.552988
+Epoch [47], train_loss: 0.071047, val_loss: 0.069199, val_acc: 23.466047
+Epoch [48], train_loss: 0.070727, val_loss: 0.067935, val_acc: 22.608906
+Epoch [49], train_loss: 0.070310, val_loss: 0.067715, val_acc: 23.558031
+Epoch [50], train_loss: 0.069891, val_loss: 0.066181, val_acc: 23.634415
+Epoch [51], train_loss: 0.069491, val_loss: 0.068604, val_acc: 23.149879
+Epoch [52], train_loss: 0.068916, val_loss: 0.067317, val_acc: 23.339506
+Epoch [53], train_loss: 0.068665, val_loss: 0.065001, val_acc: 23.746122
+Epoch [54], train_loss: 0.068175, val_loss: 0.066551, val_acc: 23.643093
+Epoch [55], train_loss: 0.067938, val_loss: 0.067875, val_acc: 23.071741
+Epoch [56], train_loss: 0.067577, val_loss: 0.068043, val_acc: 23.394621
+Epoch [57], train_loss: 0.067060, val_loss: 0.066372, val_acc: 23.600584
+Epoch [58], train_loss: 0.066781, val_loss: 0.065759, val_acc: 23.355618
+Epoch [59], train_loss: 0.066581, val_loss: 0.066743, val_acc: 23.487972
+Epoch [60], train_loss: 0.066286, val_loss: 0.066003, val_acc: 23.704594
+Epoch [61], train_loss: 0.066045, val_loss: 0.066899, val_acc: 23.678455
+Epoch [62], train_loss: 0.065701, val_loss: 0.064742, val_acc: 23.765450
+Epoch [63], train_loss: 0.065331, val_loss: 0.062848, val_acc: 23.706650
+Epoch [64], train_loss: 0.064834, val_loss: 0.063924, val_acc: 23.727221
+Epoch [65], train_loss: 0.064547, val_loss: 0.065064, val_acc: 23.711784
+Epoch [66], train_loss: 0.064281, val_loss: 0.064495, val_acc: 23.469910
+Epoch [67], train_loss: 0.063960, val_loss: 0.065959, val_acc: 23.610884
+Epoch [68], train_loss: 0.063735, val_loss: 0.065021, val_acc: 23.562294
+Epoch [69], train_loss: 0.063572, val_loss: 0.066095, val_acc: 23.488998
+Epoch [70], train_loss: 0.063277, val_loss: 0.064639, val_acc: 23.624556
+Epoch [71], train_loss: 0.062891, val_loss: 0.066996, val_acc: 23.336441
+Epoch [72], train_loss: 0.062579, val_loss: 0.063195, val_acc: 23.609161
+Epoch [73], train_loss: 0.062198, val_loss: 0.064585, val_acc: 23.646460
+Epoch [74], train_loss: 0.062242, val_loss: 0.064909, val_acc: 23.550859
+Epoch [75], train_loss: 0.062057, val_loss: 0.062923, val_acc: 23.653503
+Epoch [76], train_loss: 0.061717, val_loss: 0.066740, val_acc: 23.273527
+Epoch [77], train_loss: 0.061563, val_loss: 0.064934, val_acc: 23.616581
+Epoch [78], train_loss: 0.061469, val_loss: 0.062836, val_acc: 23.677689
+Epoch [79], train_loss: 0.061189, val_loss: 0.064261, val_acc: 23.635620
+Epoch [80], train_loss: 0.060849, val_loss: 0.063492, val_acc: 23.381968
+Epoch [81], train_loss: 0.060729, val_loss: 0.064925, val_acc: 23.432051
+Epoch [82], train_loss: 0.060419, val_loss: 0.062954, val_acc: 23.642927
+Epoch [83], train_loss: 0.060262, val_loss: 0.066476, val_acc: 23.554218
+Epoch [84], train_loss: 0.059972, val_loss: 0.064331, val_acc: 23.449234
+Epoch [85], train_loss: 0.059876, val_loss: 0.065110, val_acc: 23.256565
+Epoch [86], train_loss: 0.059947, val_loss: 0.066546, val_acc: 23.058985
+Epoch [87], train_loss: 0.059814, val_loss: 0.064508, val_acc: 23.531034
+Epoch [88], train_loss: 0.059415, val_loss: 0.062222, val_acc: 23.598854
+Epoch [89], train_loss: 0.059292, val_loss: 0.065836, val_acc: 23.472277
+Epoch [90], train_loss: 0.059155, val_loss: 0.062105, val_acc: 23.567497
+Epoch [91], train_loss: 0.060467, val_loss: 0.067152, val_acc: 23.058821
+Epoch [92], train_loss: 0.062818, val_loss: 0.062622, val_acc: 23.908640
+Epoch [93], train_loss: 0.061282, val_loss: 0.062265, val_acc: 23.958994
+Epoch [94], train_loss: 0.060561, val_loss: 0.062623, val_acc: 23.799265
+Epoch [95], train_loss: 0.060241, val_loss: 0.063167, val_acc: 23.732298
+Epoch [96], train_loss: 0.059941, val_loss: 0.061738, val_acc: 23.812666
+Epoch [97], train_loss: 0.059626, val_loss: 0.063617, val_acc: 23.529703
+Epoch [98], train_loss: 0.059414, val_loss: 0.062429, val_acc: 23.809393
+Epoch [99], train_loss: 0.059141, val_loss: 0.062143, val_acc: 23.717339
+Epoch [100], train_loss: 0.058965, val_loss: 0.062849, val_acc: 23.698755
+Epoch [101], train_loss: 0.058967, val_loss: 0.062048, val_acc: 23.723272
+Epoch [102], train_loss: 0.058655, val_loss: 0.061544, val_acc: 23.610909
+Epoch [103], train_loss: 0.058461, val_loss: 0.062826, val_acc: 23.628452
+Epoch [104], train_loss: 0.058371, val_loss: 0.061726, val_acc: 23.586512
+Epoch [105], train_loss: 0.058296, val_loss: 0.061967, val_acc: 23.792908
+Epoch [106], train_loss: 0.058201, val_loss: 0.062007, val_acc: 23.676991
+Epoch [107], train_loss: 0.058055, val_loss: 0.063292, val_acc: 23.641703
+Epoch [108], train_loss: 0.057839, val_loss: 0.062101, val_acc: 23.400702
+Epoch [109], train_loss: 0.057834, val_loss: 0.062361, val_acc: 23.624804
+Epoch [110], train_loss: 0.057604, val_loss: 0.062092, val_acc: 23.699417
+Epoch [111], train_loss: 0.057500, val_loss: 0.062254, val_acc: 23.552973
+Epoch [112], train_loss: 0.057469, val_loss: 0.062382, val_acc: 23.710781
+Epoch [113], train_loss: 0.057362, val_loss: 0.062376, val_acc: 23.482437
+Epoch [114], train_loss: 0.057177, val_loss: 0.061350, val_acc: 23.793983
+Epoch [115], train_loss: 0.057327, val_loss: 0.063346, val_acc: 23.481104
+Epoch [116], train_loss: 0.057187, val_loss: 0.062010, val_acc: 23.706173
+Epoch [117], train_loss: 0.057014, val_loss: 0.061601, val_acc: 23.675621
+Epoch [118], train_loss: 0.056910, val_loss: 0.061610, val_acc: 23.589659
+Epoch [119], train_loss: 0.056869, val_loss: 0.061946, val_acc: 23.490414
+Epoch [120], train_loss: 0.056781, val_loss: 0.061615, val_acc: 23.702793
+Epoch [121], train_loss: 0.056783, val_loss: 0.061622, val_acc: 23.461136
+Epoch [122], train_loss: 0.056629, val_loss: 0.062047, val_acc: 23.440369
+Epoch [123], train_loss: 0.056555, val_loss: 0.062068, val_acc: 23.609409
+Epoch [124], train_loss: 0.056595, val_loss: 0.061143, val_acc: 23.765024
+Epoch [125], train_loss: 0.056511, val_loss: 0.061516, val_acc: 23.683390
+Epoch [126], train_loss: 0.056416, val_loss: 0.061755, val_acc: 23.596516
+Epoch [127], train_loss: 0.056310, val_loss: 0.061139, val_acc: 23.815649
+Epoch [128], train_loss: 0.056317, val_loss: 0.062309, val_acc: 23.690243
+Epoch [129], train_loss: 0.056303, val_loss: 0.061522, val_acc: 23.580170
+Epoch [130], train_loss: 0.056173, val_loss: 0.061138, val_acc: 23.711796
+Epoch [131], train_loss: 0.056159, val_loss: 0.061152, val_acc: 23.438572
+Epoch [132], train_loss: 0.056004, val_loss: 0.062015, val_acc: 23.717087
+Epoch [133], train_loss: 0.055947, val_loss: 0.061151, val_acc: 23.859638
+Epoch [134], train_loss: 0.055907, val_loss: 0.061390, val_acc: 23.746843
+Epoch [135], train_loss: 0.055839, val_loss: 0.060703, val_acc: 23.675682
+Epoch [136], train_loss: 0.055835, val_loss: 0.061149, val_acc: 23.857780
+Epoch [137], train_loss: 0.055891, val_loss: 0.061399, val_acc: 23.683054
+Epoch [138], train_loss: 0.055725, val_loss: 0.061330, val_acc: 23.700294
+Epoch [139], train_loss: 0.055704, val_loss: 0.061146, val_acc: 23.742399
+Epoch [140], train_loss: 0.055657, val_loss: 0.061242, val_acc: 23.786512
+Epoch [141], train_loss: 0.055630, val_loss: 0.061484, val_acc: 23.790354
+Epoch [142], train_loss: 0.055623, val_loss: 0.060666, val_acc: 23.921371
+Epoch [143], train_loss: 0.055529, val_loss: 0.061637, val_acc: 23.597136
+Epoch [144], train_loss: 0.055491, val_loss: 0.060894, val_acc: 23.792538
+Epoch [145], train_loss: 0.055441, val_loss: 0.061383, val_acc: 23.632587
+Epoch [146], train_loss: 0.055407, val_loss: 0.060963, val_acc: 23.608366
+Epoch [147], train_loss: 0.055393, val_loss: 0.061007, val_acc: 23.777391
+Epoch [148], train_loss: 0.055365, val_loss: 0.061209, val_acc: 23.734245
+Epoch [149], train_loss: 0.055344, val_loss: 0.060977, val_acc: 23.671366
+Epoch [150], train_loss: 0.055227, val_loss: 0.060809, val_acc: 23.895481
+Epoch [151], train_loss: 0.055207, val_loss: 0.061323, val_acc: 23.645597
+Epoch [152], train_loss: 0.055154, val_loss: 0.060963, val_acc: 23.761339
+Epoch [153], train_loss: 0.055211, val_loss: 0.060863, val_acc: 23.794052
+Epoch [154], train_loss: 0.055134, val_loss: 0.061606, val_acc: 23.696173
+Epoch [155], train_loss: 0.055154, val_loss: 0.061140, val_acc: 23.733421
+Epoch [156], train_loss: 0.055075, val_loss: 0.061318, val_acc: 23.814327
+Epoch [157], train_loss: 0.054935, val_loss: 0.060853, val_acc: 23.747799
+Epoch [158], train_loss: 0.055036, val_loss: 0.061330, val_acc: 23.633480
+Epoch [159], train_loss: 0.054984, val_loss: 0.061097, val_acc: 23.694914
+Epoch [160], train_loss: 0.054899, val_loss: 0.060791, val_acc: 23.816675
+Epoch [161], train_loss: 0.055983, val_loss: 0.060942, val_acc: 23.746326
+Epoch [162], train_loss: 0.055674, val_loss: 0.060590, val_acc: 23.648445
+Epoch [163], train_loss: 0.055229, val_loss: 0.060664, val_acc: 23.832220
+Epoch [164], train_loss: 0.055051, val_loss: 0.060808, val_acc: 23.637949
+Epoch [165], train_loss: 0.055049, val_loss: 0.060587, val_acc: 23.833717
+Epoch [166], train_loss: 0.054944, val_loss: 0.060868, val_acc: 23.777187
+Epoch [167], train_loss: 0.054818, val_loss: 0.060629, val_acc: 23.770617
+Epoch [168], train_loss: 0.054830, val_loss: 0.060872, val_acc: 23.720793
+Epoch [169], train_loss: 0.054782, val_loss: 0.061023, val_acc: 23.581915
+Epoch [170], train_loss: 0.054702, val_loss: 0.060707, val_acc: 23.757950
+Epoch [171], train_loss: 0.054667, val_loss: 0.060680, val_acc: 23.803095
+Epoch [172], train_loss: 0.054664, val_loss: 0.060561, val_acc: 23.795202
+Epoch [173], train_loss: 0.054604, val_loss: 0.061209, val_acc: 23.643259
+Epoch [174], train_loss: 0.054569, val_loss: 0.060937, val_acc: 23.800205
+Epoch [175], train_loss: 0.054506, val_loss: 0.060967, val_acc: 23.828989
+Epoch [176], train_loss: 0.054473, val_loss: 0.060562, val_acc: 23.818304
+Epoch [177], train_loss: 0.054496, val_loss: 0.061081, val_acc: 23.757412
+Epoch [178], train_loss: 0.054441, val_loss: 0.060755, val_acc: 23.888472
+Epoch [179], train_loss: 0.054382, val_loss: 0.060906, val_acc: 23.849545
+Epoch [180], train_loss: 0.054422, val_loss: 0.060684, val_acc: 23.766418
+Epoch [181], train_loss: 0.054379, val_loss: 0.060786, val_acc: 23.572336
+Epoch [182], train_loss: 0.054267, val_loss: 0.060844, val_acc: 23.703535
+Epoch [183], train_loss: 0.054339, val_loss: 0.061163, val_acc: 23.688438
+Epoch [184], train_loss: 0.054251, val_loss: 0.061375, val_acc: 23.729029
+Epoch [185], train_loss: 0.054254, val_loss: 0.060506, val_acc: 23.827196
+Epoch [186], train_loss: 0.054192, val_loss: 0.060834, val_acc: 23.820234
+Epoch [187], train_loss: 0.054132, val_loss: 0.060893, val_acc: 23.760778
+Epoch [188], train_loss: 0.054171, val_loss: 0.061498, val_acc: 23.589100
+Epoch [189], train_loss: 0.054067, val_loss: 0.060883, val_acc: 23.856726
+Epoch [190], train_loss: 0.054038, val_loss: 0.061006, val_acc: 23.575039
+Epoch [191], train_loss: 0.054032, val_loss: 0.060672, val_acc: 23.748226
+Epoch [192], train_loss: 0.054018, val_loss: 0.060992, val_acc: 23.588179
+Epoch [193], train_loss: 0.054056, val_loss: 0.060805, val_acc: 23.765278
+Epoch [194], train_loss: 0.054020, val_loss: 0.060688, val_acc: 23.780149
+Epoch [195], train_loss: 0.054080, val_loss: 0.061019, val_acc: 23.422661
+Epoch [196], train_loss: 0.053941, val_loss: 0.061167, val_acc: 23.775200
+Epoch [197], train_loss: 0.053988, val_loss: 0.060755, val_acc: 23.628098
+Epoch [198], train_loss: 0.053814, val_loss: 0.060540, val_acc: 23.755655
+Epoch [199], train_loss: 0.053875, val_loss: 0.061136, val_acc: 23.770569
+Epoch [200], train_loss: 0.053853, val_loss: 0.061056, val_acc: 23.571482
+Epoch [201], train_loss: 0.053805, val_loss: 0.061034, val_acc: 23.567881
+Epoch [202], train_loss: 0.053781, val_loss: 0.061040, val_acc: 23.645098
+Epoch [203], train_loss: 0.053769, val_loss: 0.061042, val_acc: 23.497137
+Epoch [204], train_loss: 0.053726, val_loss: 0.060846, val_acc: 23.757725
+Epoch [205], train_loss: 0.053745, val_loss: 0.061055, val_acc: 23.341063
+Epoch [206], train_loss: 0.053654, val_loss: 0.061318, val_acc: 23.397654
+Epoch [207], train_loss: 0.053665, val_loss: 0.060807, val_acc: 23.652542
+Epoch [208], train_loss: 0.053637, val_loss: 0.061084, val_acc: 23.557011
+Epoch [209], train_loss: 0.053589, val_loss: 0.061058, val_acc: 23.573685
+Epoch [210], train_loss: 0.053557, val_loss: 0.061327, val_acc: 23.621185
+Epoch [211], train_loss: 0.053519, val_loss: 0.061003, val_acc: 23.431120
+Epoch [212], train_loss: 0.053507, val_loss: 0.061043, val_acc: 23.754984
+Epoch [213], train_loss: 0.053469, val_loss: 0.060916, val_acc: 23.645691
+Epoch [214], train_loss: 0.053451, val_loss: 0.060961, val_acc: 23.741211
+Epoch [215], train_loss: 0.053450, val_loss: 0.060899, val_acc: 23.640867
+Epoch [216], train_loss: 0.053393, val_loss: 0.060831, val_acc: 23.631128
+Epoch [217], train_loss: 0.053430, val_loss: 0.061637, val_acc: 23.610020
+Epoch [218], train_loss: 0.053450, val_loss: 0.061565, val_acc: 23.589207
+Epoch [219], train_loss: 0.053410, val_loss: 0.060921, val_acc: 23.714334
+Epoch [220], train_loss: 0.053354, val_loss: 0.061209, val_acc: 23.624598
+Epoch [221], train_loss: 0.053287, val_loss: 0.060658, val_acc: 23.669712
+Epoch [222], train_loss: 0.053229, val_loss: 0.060839, val_acc: 23.723066
+Epoch [223], train_loss: 0.053248, val_loss: 0.060974, val_acc: 23.653633
+Epoch [224], train_loss: 0.053225, val_loss: 0.061045, val_acc: 23.554737
+Epoch [225], train_loss: 0.053198, val_loss: 0.060866, val_acc: 23.611935
+Epoch [226], train_loss: 0.053199, val_loss: 0.061270, val_acc: 23.576006
+Epoch [227], train_loss: 0.053178, val_loss: 0.061186, val_acc: 23.424984
+Epoch [228], train_loss: 0.053133, val_loss: 0.060982, val_acc: 23.639156
+Epoch [229], train_loss: 0.053125, val_loss: 0.061176, val_acc: 23.613422
+Epoch [230], train_loss: 0.053069, val_loss: 0.061453, val_acc: 23.398228
+Epoch [231], train_loss: 0.053042, val_loss: 0.061493, val_acc: 23.557688
+Epoch [232], train_loss: 0.053053, val_loss: 0.061361, val_acc: 23.413322
+Epoch [233], train_loss: 0.053036, val_loss: 0.061099, val_acc: 23.470411
+Epoch [234], train_loss: 0.053000, val_loss: 0.061138, val_acc: 23.418964
+Epoch [235], train_loss: 0.052947, val_loss: 0.061361, val_acc: 23.652473
+Epoch [236], train_loss: 0.052974, val_loss: 0.060898, val_acc: 23.475117
+Epoch [237], train_loss: 0.052928, val_loss: 0.061057, val_acc: 23.451942
+Epoch [238], train_loss: 0.052940, val_loss: 0.061190, val_acc: 23.609123
+Epoch [239], train_loss: 0.052861, val_loss: 0.061467, val_acc: 23.328365
+Epoch [240], train_loss: 0.052866, val_loss: 0.061088, val_acc: 23.553154
+Epoch [241], train_loss: 0.052821, val_loss: 0.061354, val_acc: 23.519932
+Epoch [242], train_loss: 0.052784, val_loss: 0.061192, val_acc: 23.602512
+Epoch [243], train_loss: 0.052749, val_loss: 0.060841, val_acc: 23.627773
+Epoch [244], train_loss: 0.052694, val_loss: 0.061155, val_acc: 23.457624
+Epoch [245], train_loss: 0.052841, val_loss: 0.060993, val_acc: 23.559929
+Epoch [246], train_loss: 0.052762, val_loss: 0.060824, val_acc: 23.582727
+Epoch [247], train_loss: 0.052720, val_loss: 0.061083, val_acc: 23.671101
+Epoch [248], train_loss: 0.052699, val_loss: 0.061201, val_acc: 23.611851
+Epoch [249], train_loss: 0.052669, val_loss: 0.060885, val_acc: 23.526703
+Epoch [250], train_loss: 0.052591, val_loss: 0.060796, val_acc: 23.556065
+Epoch [251], train_loss: 0.052580, val_loss: 0.061019, val_acc: 23.580595
+Epoch [252], train_loss: 0.052546, val_loss: 0.060884, val_acc: 23.632748
+Epoch [253], train_loss: 0.052580, val_loss: 0.061027, val_acc: 23.671726
+Epoch [254], train_loss: 0.052496, val_loss: 0.061339, val_acc: 23.690750
+Epoch [255], train_loss: 0.052439, val_loss: 0.061204, val_acc: 23.503046
+Epoch [256], train_loss: 0.052436, val_loss: 0.060683, val_acc: 23.681074
+Epoch [257], train_loss: 0.052477, val_loss: 0.061950, val_acc: 23.433817
+Epoch [258], train_loss: 0.052422, val_loss: 0.060822, val_acc: 23.552477
+Epoch [259], train_loss: 0.052354, val_loss: 0.061061, val_acc: 23.666336
+Epoch [260], train_loss: 0.052372, val_loss: 0.061758, val_acc: 23.462681
+Epoch [261], train_loss: 0.052350, val_loss: 0.061161, val_acc: 23.456238
+Epoch [262], train_loss: 0.052239, val_loss: 0.061314, val_acc: 23.397467
+Epoch [263], train_loss: 0.052327, val_loss: 0.061320, val_acc: 23.423988
+Epoch [264], train_loss: 0.052239, val_loss: 0.060989, val_acc: 23.447693
+Epoch [265], train_loss: 0.052186, val_loss: 0.061216, val_acc: 23.265766
+Epoch [266], train_loss: 0.052230, val_loss: 0.061086, val_acc: 23.435337
+Epoch [267], train_loss: 0.052265, val_loss: 0.061235, val_acc: 23.384766
+Epoch [268], train_loss: 0.052181, val_loss: 0.061398, val_acc: 23.536150
+Epoch [269], train_loss: 0.052138, val_loss: 0.061103, val_acc: 23.585642
+Epoch [270], train_loss: 0.052189, val_loss: 0.061336, val_acc: 23.589300
+Epoch [271], train_loss: 0.052146, val_loss: 0.062142, val_acc: 23.205393
+Epoch [272], train_loss: 0.052405, val_loss: 0.061297, val_acc: 23.550922
+Epoch [273], train_loss: 0.052166, val_loss: 0.060857, val_acc: 23.491169
+Epoch [274], train_loss: 0.052018, val_loss: 0.061070, val_acc: 23.240812
+Epoch [275], train_loss: 0.052005, val_loss: 0.061134, val_acc: 23.456591
+Epoch [276], train_loss: 0.051966, val_loss: 0.061351, val_acc: 23.517759
+Epoch [277], train_loss: 0.051968, val_loss: 0.060988, val_acc: 23.489882
+Epoch [278], train_loss: 0.051985, val_loss: 0.061709, val_acc: 23.452734
+Epoch [279], train_loss: 0.051906, val_loss: 0.061241, val_acc: 23.464064
+Epoch [280], train_loss: 0.051959, val_loss: 0.061246, val_acc: 23.427238
+Epoch [281], train_loss: 0.051834, val_loss: 0.061467, val_acc: 23.268753
+Epoch [282], train_loss: 0.051828, val_loss: 0.061004, val_acc: 23.544987
+Epoch [283], train_loss: 0.051864, val_loss: 0.061196, val_acc: 23.359573
+Epoch [284], train_loss: 0.051806, val_loss: 0.061431, val_acc: 23.285805
+Epoch [285], train_loss: 0.051720, val_loss: 0.061016, val_acc: 23.459883
+Epoch [286], train_loss: 0.051769, val_loss: 0.061811, val_acc: 23.098047
+Epoch [287], train_loss: 0.051744, val_loss: 0.061386, val_acc: 23.318111
+Epoch [288], train_loss: 0.051782, val_loss: 0.061116, val_acc: 23.429962
+Epoch [289], train_loss: 0.051646, val_loss: 0.061341, val_acc: 23.309238
+Epoch [290], train_loss: 0.051631, val_loss: 0.061089, val_acc: 23.336033
+Epoch [291], train_loss: 0.051598, val_loss: 0.061037, val_acc: 23.380491
+Epoch [292], train_loss: 0.051600, val_loss: 0.061282, val_acc: 23.388752
+Epoch [293], train_loss: 0.051649, val_loss: 0.061111, val_acc: 23.474262
+Epoch [294], train_loss: 0.051541, val_loss: 0.061273, val_acc: 23.248695
+Epoch [295], train_loss: 0.051620, val_loss: 0.061391, val_acc: 23.332445
+Epoch [296], train_loss: 0.051527, val_loss: 0.061383, val_acc: 23.305994
+Epoch [297], train_loss: 0.051499, val_loss: 0.061530, val_acc: 23.203609
+Epoch [298], train_loss: 0.051435, val_loss: 0.061417, val_acc: 23.367807
+Epoch [299], train_loss: 0.051470, val_loss: 0.061288, val_acc: 23.401222
+Epoch [300], train_loss: 0.051481, val_loss: 0.061237, val_acc: 23.360107
+Epoch [301], train_loss: 0.051342, val_loss: 0.061107, val_acc: 23.325785
+Epoch [302], train_loss: 0.051382, val_loss: 0.061135, val_acc: 23.512598
+Epoch [303], train_loss: 0.051388, val_loss: 0.061628, val_acc: 23.287298
+Epoch [304], train_loss: 0.051313, val_loss: 0.061206, val_acc: 23.196882
+Epoch [305], train_loss: 0.051276, val_loss: 0.061326, val_acc: 23.444759
+Epoch [306], train_loss: 0.051284, val_loss: 0.061264, val_acc: 23.288204
+Epoch [307], train_loss: 0.051219, val_loss: 0.061288, val_acc: 23.220264
+Epoch [308], train_loss: 0.051227, val_loss: 0.061222, val_acc: 23.377781
+Epoch [309], train_loss: 0.051247, val_loss: 0.061619, val_acc: 23.084314
+Epoch [310], train_loss: 0.051243, val_loss: 0.061317, val_acc: 23.410467
+Epoch [311], train_loss: 0.051207, val_loss: 0.061507, val_acc: 23.203154
+Epoch [312], train_loss: 0.051173, val_loss: 0.061637, val_acc: 23.230558
+Epoch [313], train_loss: 0.051161, val_loss: 0.061728, val_acc: 23.215973
+Epoch [314], train_loss: 0.051037, val_loss: 0.061369, val_acc: 23.366255
+Epoch [315], train_loss: 0.051088, val_loss: 0.061621, val_acc: 23.162107
+Epoch [316], train_loss: 0.051016, val_loss: 0.061355, val_acc: 23.263931
+Epoch [317], train_loss: 0.051069, val_loss: 0.061425, val_acc: 23.240334
+Epoch [318], train_loss: 0.050996, val_loss: 0.061590, val_acc: 23.245598
+Epoch [319], train_loss: 0.050986, val_loss: 0.061220, val_acc: 23.363224
+Epoch [320], train_loss: 0.051042, val_loss: 0.061457, val_acc: 23.272568
+Epoch [321], train_loss: 0.051115, val_loss: 0.061635, val_acc: 23.212666
+Epoch [322], train_loss: 0.051009, val_loss: 0.061396, val_acc: 23.139349
+Epoch [323], train_loss: 0.050935, val_loss: 0.061693, val_acc: 23.136946
+Epoch [324], train_loss: 0.050875, val_loss: 0.061573, val_acc: 23.182585
+Epoch [325], train_loss: 0.051000, val_loss: 0.061441, val_acc: 23.174660
+Epoch [326], train_loss: 0.050911, val_loss: 0.061634, val_acc: 23.241463
+Epoch [327], train_loss: 0.050809, val_loss: 0.061505, val_acc: 23.098469
+Epoch [328], train_loss: 0.050823, val_loss: 0.061480, val_acc: 23.252020
+Epoch [329], train_loss: 0.050699, val_loss: 0.061754, val_acc: 23.136549
+Epoch [330], train_loss: 0.050737, val_loss: 0.062177, val_acc: 23.069412
+Epoch [331], train_loss: 0.050691, val_loss: 0.061843, val_acc: 23.093500
+Epoch [332], train_loss: 0.050732, val_loss: 0.061730, val_acc: 23.021574
+Epoch [333], train_loss: 0.050687, val_loss: 0.061793, val_acc: 23.122362
+Epoch [334], train_loss: 0.050690, val_loss: 0.061893, val_acc: 23.031044
+Epoch [335], train_loss: 0.050591, val_loss: 0.061747, val_acc: 23.170815
+Epoch [336], train_loss: 0.050562, val_loss: 0.061795, val_acc: 23.071323
+Epoch [337], train_loss: 0.050619, val_loss: 0.061619, val_acc: 23.184858
+Epoch [338], train_loss: 0.050525, val_loss: 0.061565, val_acc: 23.179731
+Epoch [339], train_loss: 0.050527, val_loss: 0.061690, val_acc: 22.998804
+Epoch [340], train_loss: 0.050514, val_loss: 0.061711, val_acc: 23.035944
+Epoch [341], train_loss: 0.050455, val_loss: 0.061874, val_acc: 22.977892
+Epoch [342], train_loss: 0.050440, val_loss: 0.061722, val_acc: 23.118752
+Epoch [343], train_loss: 0.053863, val_loss: 0.061537, val_acc: 23.439259
+Epoch [344], train_loss: 0.053766, val_loss: 0.061149, val_acc: 23.322697
+Epoch [345], train_loss: 0.052619, val_loss: 0.061352, val_acc: 23.176620
+Epoch [346], train_loss: 0.051999, val_loss: 0.061758, val_acc: 23.080441
+Epoch [347], train_loss: 0.051599, val_loss: 0.061759, val_acc: 22.888166
+Epoch [348], train_loss: 0.051416, val_loss: 0.061740, val_acc: 23.116917
+Epoch [349], train_loss: 0.051189, val_loss: 0.061630, val_acc: 23.231178
+Epoch [350], train_loss: 0.051182, val_loss: 0.061372, val_acc: 23.247385
+Epoch [351], train_loss: 0.050989, val_loss: 0.061645, val_acc: 23.103504
+Epoch [352], train_loss: 0.050881, val_loss: 0.061839, val_acc: 23.007166
+Epoch [353], train_loss: 0.050915, val_loss: 0.061582, val_acc: 23.094236
+Epoch [354], train_loss: 0.050708, val_loss: 0.061741, val_acc: 23.027580
+Epoch [355], train_loss: 0.050640, val_loss: 0.061623, val_acc: 23.163214
+Epoch [356], train_loss: 0.050648, val_loss: 0.061817, val_acc: 23.084587
+Epoch [357], train_loss: 0.050565, val_loss: 0.061691, val_acc: 22.954905
+Epoch [358], train_loss: 0.050498, val_loss: 0.061749, val_acc: 23.222137
+Epoch [359], train_loss: 0.050552, val_loss: 0.061653, val_acc: 23.087164
+Epoch [360], train_loss: 0.050552, val_loss: 0.061894, val_acc: 22.930952
+Epoch [361], train_loss: 0.050464, val_loss: 0.061975, val_acc: 22.791798
+Epoch [362], train_loss: 0.050382, val_loss: 0.061818, val_acc: 23.070877
+Epoch [363], train_loss: 0.050360, val_loss: 0.061899, val_acc: 22.926514
+Epoch [364], train_loss: 0.050400, val_loss: 0.061771, val_acc: 22.999264
+Epoch [365], train_loss: 0.050341, val_loss: 0.061825, val_acc: 23.022438
+Epoch [366], train_loss: 0.050275, val_loss: 0.061874, val_acc: 23.138910
+Epoch [367], train_loss: 0.050264, val_loss: 0.061727, val_acc: 23.047905
+Epoch [368], train_loss: 0.050327, val_loss: 0.061590, val_acc: 23.150654
+Epoch [369], train_loss: 0.050268, val_loss: 0.061692, val_acc: 23.074642
+Epoch [370], train_loss: 0.050286, val_loss: 0.061772, val_acc: 23.177464
+Epoch [371], train_loss: 0.050221, val_loss: 0.061877, val_acc: 23.043077
+Epoch [372], train_loss: 0.050205, val_loss: 0.061563, val_acc: 23.143833
+Epoch [373], train_loss: 0.050250, val_loss: 0.061861, val_acc: 23.029917
+Epoch [374], train_loss: 0.050216, val_loss: 0.061808, val_acc: 22.994860
+Epoch [375], train_loss: 0.050106, val_loss: 0.061779, val_acc: 22.956348
+Epoch [376], train_loss: 0.050108, val_loss: 0.061926, val_acc: 22.941084
+Epoch [377], train_loss: 0.050097, val_loss: 0.061865, val_acc: 23.046015
+Epoch [378], train_loss: 0.050110, val_loss: 0.061718, val_acc: 22.990147
+Epoch [379], train_loss: 0.050042, val_loss: 0.061722, val_acc: 23.114021
+Epoch [380], train_loss: 0.050032, val_loss: 0.061642, val_acc: 23.083549
+Epoch [381], train_loss: 0.050120, val_loss: 0.061676, val_acc: 23.215441
+Epoch [382], train_loss: 0.049989, val_loss: 0.061740, val_acc: 23.039568
+Epoch [383], train_loss: 0.049953, val_loss: 0.061958, val_acc: 23.013447
+Epoch [384], train_loss: 0.049956, val_loss: 0.061891, val_acc: 22.986631
+Epoch [385], train_loss: 0.049933, val_loss: 0.062110, val_acc: 22.917252
+Epoch [386], train_loss: 0.050007, val_loss: 0.062005, val_acc: 22.907490
+Epoch [387], train_loss: 0.049959, val_loss: 0.061664, val_acc: 23.054276
+Epoch [388], train_loss: 0.049988, val_loss: 0.062251, val_acc: 22.873846
+Epoch [389], train_loss: 0.049886, val_loss: 0.061834, val_acc: 23.000393
+Epoch [390], train_loss: 0.049826, val_loss: 0.062017, val_acc: 22.993864
+Epoch [391], train_loss: 0.049881, val_loss: 0.062001, val_acc: 23.052408
+Epoch [392], train_loss: 0.049785, val_loss: 0.061953, val_acc: 22.904331
+Epoch [393], train_loss: 0.049857, val_loss: 0.062069, val_acc: 22.820747
+Epoch [394], train_loss: 0.049836, val_loss: 0.062055, val_acc: 22.911665
+Epoch [395], train_loss: 0.049837, val_loss: 0.062043, val_acc: 22.881487
+Epoch [396], train_loss: 0.049784, val_loss: 0.061938, val_acc: 23.061478
+Epoch [397], train_loss: 0.049713, val_loss: 0.061926, val_acc: 23.111094
+Epoch [398], train_loss: 0.049690, val_loss: 0.061818, val_acc: 23.048988
+Epoch [399], train_loss: 0.049779, val_loss: 0.061975, val_acc: 22.949724
+Epoch [400], train_loss: 0.049750, val_loss: 0.061977, val_acc: 22.980648
+Epoch [401], train_loss: 0.049683, val_loss: 0.061940, val_acc: 23.013935
+Epoch [402], train_loss: 0.049643, val_loss: 0.062273, val_acc: 22.932463
+Epoch [403], train_loss: 0.049672, val_loss: 0.062334, val_acc: 22.773279
+Epoch [404], train_loss: 0.049648, val_loss: 0.061789, val_acc: 23.118574
+Epoch [405], train_loss: 0.049595, val_loss: 0.062046, val_acc: 22.926985
+Epoch [406], train_loss: 0.049589, val_loss: 0.062132, val_acc: 23.043007
+Epoch [407], train_loss: 0.049590, val_loss: 0.062093, val_acc: 22.897911
+Epoch [408], train_loss: 0.049611, val_loss: 0.061985, val_acc: 22.945454
+Epoch [409], train_loss: 0.049510, val_loss: 0.062136, val_acc: 23.159424
+Epoch [410], train_loss: 0.049544, val_loss: 0.062209, val_acc: 22.885004
+Epoch [411], train_loss: 0.049515, val_loss: 0.062263, val_acc: 22.880424
+Epoch [412], train_loss: 0.049417, val_loss: 0.062099, val_acc: 22.871170
+Epoch [413], train_loss: 0.049484, val_loss: 0.062000, val_acc: 22.894672
+Epoch [414], train_loss: 0.049477, val_loss: 0.062045, val_acc: 22.993639
+Epoch [415], train_loss: 0.049480, val_loss: 0.062295, val_acc: 22.948174
+Epoch [416], train_loss: 0.049443, val_loss: 0.062011, val_acc: 23.004156
+Epoch [417], train_loss: 0.049476, val_loss: 0.062290, val_acc: 22.877110
+Epoch [418], train_loss: 0.049453, val_loss: 0.062211, val_acc: 22.920908
+Epoch [419], train_loss: 0.049406, val_loss: 0.062322, val_acc: 22.853271
+Epoch [420], train_loss: 0.049380, val_loss: 0.062144, val_acc: 22.962910
+Epoch [421], train_loss: 0.049299, val_loss: 0.062297, val_acc: 22.911039
+Epoch [422], train_loss: 0.049371, val_loss: 0.062492, val_acc: 22.861084
+Epoch [423], train_loss: 0.049295, val_loss: 0.062097, val_acc: 22.947666
+Epoch [424], train_loss: 0.049274, val_loss: 0.062173, val_acc: 22.947773
+Epoch [425], train_loss: 0.049294, val_loss: 0.062245, val_acc: 22.884443
+Epoch [426], train_loss: 0.049340, val_loss: 0.062201, val_acc: 23.022999
+Epoch [427], train_loss: 0.049239, val_loss: 0.062309, val_acc: 22.860447
+Epoch [428], train_loss: 0.049181, val_loss: 0.062175, val_acc: 22.868315
+Epoch [429], train_loss: 0.049190, val_loss: 0.062385, val_acc: 22.857841
+Epoch [430], train_loss: 0.049331, val_loss: 0.062350, val_acc: 22.825037
+Epoch [431], train_loss: 0.049232, val_loss: 0.062347, val_acc: 22.931547
+Epoch [432], train_loss: 0.049201, val_loss: 0.062131, val_acc: 22.939377
+Epoch [433], train_loss: 0.049229, val_loss: 0.062261, val_acc: 22.929003
+Epoch [434], train_loss: 0.049184, val_loss: 0.062294, val_acc: 22.916338
+Epoch [435], train_loss: 0.049229, val_loss: 0.062315, val_acc: 22.973242
+Epoch [436], train_loss: 0.049105, val_loss: 0.062400, val_acc: 22.721983
+Epoch [437], train_loss: 0.049058, val_loss: 0.062421, val_acc: 22.892099
+Epoch [438], train_loss: 0.049068, val_loss: 0.062603, val_acc: 22.630198
+Epoch [439], train_loss: 0.049008, val_loss: 0.062147, val_acc: 22.924500
+Epoch [440], train_loss: 0.049007, val_loss: 0.061951, val_acc: 23.162468
+Epoch [441], train_loss: 0.048997, val_loss: 0.062345, val_acc: 22.872980
+Epoch [442], train_loss: 0.048938, val_loss: 0.062385, val_acc: 22.837214
+Epoch [443], train_loss: 0.048923, val_loss: 0.062179, val_acc: 22.958754
+Epoch [444], train_loss: 0.048934, val_loss: 0.062443, val_acc: 22.926603
+Epoch [445], train_loss: 0.048884, val_loss: 0.062525, val_acc: 22.861317
+Epoch [446], train_loss: 0.048957, val_loss: 0.062578, val_acc: 22.697111
+Epoch [447], train_loss: 0.048901, val_loss: 0.062500, val_acc: 22.858465
+Epoch [448], train_loss: 0.048939, val_loss: 0.062344, val_acc: 22.868231
+Epoch [449], train_loss: 0.048835, val_loss: 0.062663, val_acc: 22.796824
+Epoch [450], train_loss: 0.048819, val_loss: 0.062444, val_acc: 22.914238
+Epoch [451], train_loss: 0.048777, val_loss: 0.062550, val_acc: 22.877831
+Epoch [452], train_loss: 0.048842, val_loss: 0.062546, val_acc: 22.986010
+Epoch [453], train_loss: 0.048896, val_loss: 0.062338, val_acc: 22.922272
+Epoch [454], train_loss: 0.048787, val_loss: 0.062497, val_acc: 22.779537
+Epoch [455], train_loss: 0.048709, val_loss: 0.062485, val_acc: 22.879452
+Epoch [456], train_loss: 0.048708, val_loss: 0.062524, val_acc: 22.930141
+Epoch [457], train_loss: 0.048682, val_loss: 0.062379, val_acc: 22.999975
+Epoch [458], train_loss: 0.048730, val_loss: 0.062318, val_acc: 22.816923
+Epoch [459], train_loss: 0.048754, val_loss: 0.062779, val_acc: 22.851099
+Epoch [460], train_loss: 0.048675, val_loss: 0.062531, val_acc: 22.827778
+Epoch [461], train_loss: 0.048710, val_loss: 0.062712, val_acc: 22.668167
+Epoch [462], train_loss: 0.048592, val_loss: 0.062585, val_acc: 22.747532
+Epoch [463], train_loss: 0.048651, val_loss: 0.062681, val_acc: 22.933655
+Epoch [464], train_loss: 0.048647, val_loss: 0.062489, val_acc: 22.857700
+Epoch [465], train_loss: 0.048645, val_loss: 0.062714, val_acc: 22.800035
+Epoch [466], train_loss: 0.048561, val_loss: 0.062431, val_acc: 22.831461
+Epoch [467], train_loss: 0.048473, val_loss: 0.062437, val_acc: 22.853489
+Epoch [468], train_loss: 0.048511, val_loss: 0.062489, val_acc: 22.850296
+Epoch [469], train_loss: 0.048433, val_loss: 0.062698, val_acc: 22.718132
+Epoch [470], train_loss: 0.048487, val_loss: 0.062434, val_acc: 22.989836
+Epoch [471], train_loss: 0.048435, val_loss: 0.062713, val_acc: 22.713192
+Epoch [472], train_loss: 0.048535, val_loss: 0.062319, val_acc: 22.960602
+Epoch [473], train_loss: 0.048443, val_loss: 0.062607, val_acc: 22.783405
+Epoch [474], train_loss: 0.048404, val_loss: 0.062612, val_acc: 22.796679
+Epoch [475], train_loss: 0.048380, val_loss: 0.062939, val_acc: 22.523552
+Epoch [476], train_loss: 0.048417, val_loss: 0.062633, val_acc: 22.828680
+Epoch [477], train_loss: 0.048399, val_loss: 0.062924, val_acc: 22.748230
+Epoch [478], train_loss: 0.048322, val_loss: 0.062475, val_acc: 22.866987
+Epoch [479], train_loss: 0.048330, val_loss: 0.062671, val_acc: 22.889606
+Epoch [480], train_loss: 0.048309, val_loss: 0.062768, val_acc: 22.787718
+Epoch [481], train_loss: 0.048287, val_loss: 0.062637, val_acc: 22.944834
+Epoch [482], train_loss: 0.048239, val_loss: 0.062817, val_acc: 22.615974
+Epoch [483], train_loss: 0.048269, val_loss: 0.062782, val_acc: 22.766066
+Epoch [484], train_loss: 0.048212, val_loss: 0.062392, val_acc: 22.916807
+Epoch [485], train_loss: 0.048194, val_loss: 0.062881, val_acc: 22.640284
+Epoch [486], train_loss: 0.048255, val_loss: 0.062630, val_acc: 22.956102
+Epoch [487], train_loss: 0.048265, val_loss: 0.062831, val_acc: 22.886290
+Epoch [488], train_loss: 0.048252, val_loss: 0.062593, val_acc: 22.907896
+Epoch [489], train_loss: 0.048086, val_loss: 0.062657, val_acc: 22.870672
+Epoch [490], train_loss: 0.048156, val_loss: 0.062861, val_acc: 22.744120
+Epoch [491], train_loss: 0.048194, val_loss: 0.062834, val_acc: 22.832432
+Epoch [492], train_loss: 0.048062, val_loss: 0.062982, val_acc: 22.603737
+Epoch [493], train_loss: 0.048084, val_loss: 0.062861, val_acc: 22.565012
+Epoch [494], train_loss: 0.048026, val_loss: 0.063298, val_acc: 22.430935
+Epoch [495], train_loss: 0.047989, val_loss: 0.062755, val_acc: 22.730911
+Epoch [496], train_loss: 0.048052, val_loss: 0.062945, val_acc: 22.674749
+Epoch [497], train_loss: 0.047991, val_loss: 0.062982, val_acc: 22.666691
+Epoch [498], train_loss: 0.047980, val_loss: 0.063032, val_acc: 22.690922
+Epoch [499], train_loss: 0.047975, val_loss: 0.062786, val_acc: 22.731834
+python3 ./UNet_V9_2.py  11422.38s user 10908.73s system 99% cpu 6:12:15.16 total
 number auf epochs: 500
 batchsize: 32
-learning rate: 1e-05
+learning rate: 5e-05
 kernel size is: 3
  seed is: 373686838
-Traceback (most recent call last):
-  File "./UNet_V9_3.py", line 247, in <module>
-    normalization = np.load(f'{path_to_rep}/UNet/Trainingsdata/Norm_min_max_32_angles.npy')
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/npyio.py", line 441, in load
-    pickle_kwargs=pickle_kwargs)
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/format.py", line 743, in read_array
-    raise ValueError("Object arrays cannot be loaded when "
-ValueError: Object arrays cannot be loaded when allow_pickle=False
-python3 ./UNet_V9_3.py  0.85s user 1.39s system 82% cpu 2.716 total
+Epoch [0], train_loss: 0.203403, val_loss: 0.164060, val_acc: 6.180506
+Epoch [1], train_loss: 0.181745, val_loss: 0.157765, val_acc: 10.760752
+Epoch [2], train_loss: 0.158992, val_loss: 0.145129, val_acc: 13.185714
+Epoch [3], train_loss: 0.142397, val_loss: 0.132882, val_acc: 14.721860
+Epoch [4], train_loss: 0.132609, val_loss: 0.124845, val_acc: 15.680460
+Epoch [5], train_loss: 0.125337, val_loss: 0.119166, val_acc: 16.223457
+Epoch [6], train_loss: 0.119033, val_loss: 0.112017, val_acc: 17.253199
+Epoch [7], train_loss: 0.113209, val_loss: 0.110215, val_acc: 18.263025
+Epoch [8], train_loss: 0.107897, val_loss: 0.101387, val_acc: 19.892500
+Epoch [9], train_loss: 0.103167, val_loss: 0.095610, val_acc: 20.825575
+Epoch [10], train_loss: 0.099052, val_loss: 0.094366, val_acc: 21.206751
+Epoch [11], train_loss: 0.095483, val_loss: 0.089345, val_acc: 21.683939
+Epoch [12], train_loss: 0.092342, val_loss: 0.087558, val_acc: 21.722603
+Epoch [13], train_loss: 0.089660, val_loss: 0.081062, val_acc: 22.508625
+Epoch [14], train_loss: 0.087394, val_loss: 0.087235, val_acc: 21.840553
+Epoch [15], train_loss: 0.085403, val_loss: 0.080297, val_acc: 22.766706
+Epoch [16], train_loss: 0.083528, val_loss: 0.076418, val_acc: 22.879108
+Epoch [17], train_loss: 0.082081, val_loss: 0.078176, val_acc: 22.666100
+Epoch [18], train_loss: 0.080684, val_loss: 0.077171, val_acc: 22.765644
+Epoch [19], train_loss: 0.079418, val_loss: 0.081791, val_acc: 22.465874
+Epoch [20], train_loss: 0.078248, val_loss: 0.076182, val_acc: 23.224720
+Epoch [21], train_loss: 0.077081, val_loss: 0.076049, val_acc: 23.150846
+Epoch [22], train_loss: 0.075939, val_loss: 0.077412, val_acc: 22.890945
+Epoch [23], train_loss: 0.075077, val_loss: 0.075096, val_acc: 23.053581
+Epoch [24], train_loss: 0.074314, val_loss: 0.073904, val_acc: 23.040573
+Epoch [25], train_loss: 0.073422, val_loss: 0.072688, val_acc: 23.456284
+Epoch [26], train_loss: 0.072919, val_loss: 0.074800, val_acc: 22.935736
+Epoch [27], train_loss: 0.072480, val_loss: 0.069964, val_acc: 23.909124
+Epoch [28], train_loss: 0.071498, val_loss: 0.072834, val_acc: 23.609558
+Epoch [29], train_loss: 0.070747, val_loss: 0.071559, val_acc: 23.675350
+Epoch [30], train_loss: 0.070097, val_loss: 0.068012, val_acc: 23.963608
+Epoch [31], train_loss: 0.069549, val_loss: 0.072962, val_acc: 23.048365
+Epoch [32], train_loss: 0.069445, val_loss: 0.067672, val_acc: 23.978746
+Epoch [33], train_loss: 0.068530, val_loss: 0.067237, val_acc: 24.104713
+Epoch [34], train_loss: 0.068143, val_loss: 0.067233, val_acc: 24.135050
+Epoch [35], train_loss: 0.067687, val_loss: 0.069958, val_acc: 23.834105
+Epoch [36], train_loss: 0.067288, val_loss: 0.067616, val_acc: 24.077826
+Epoch [37], train_loss: 0.066782, val_loss: 0.066489, val_acc: 24.185463
+Epoch [38], train_loss: 0.066306, val_loss: 0.066635, val_acc: 24.018055
+Epoch [39], train_loss: 0.065955, val_loss: 0.065882, val_acc: 24.254480
+Epoch [40], train_loss: 0.065534, val_loss: 0.066348, val_acc: 24.139715
+Epoch [41], train_loss: 0.065190, val_loss: 0.064348, val_acc: 24.470543
+Epoch [42], train_loss: 0.064964, val_loss: 0.065556, val_acc: 24.316172
+Epoch [43], train_loss: 0.064581, val_loss: 0.065130, val_acc: 24.313465
+Epoch [44], train_loss: 0.064353, val_loss: 0.066162, val_acc: 23.974955
+Epoch [45], train_loss: 0.063804, val_loss: 0.063421, val_acc: 24.511541
+Epoch [46], train_loss: 0.063803, val_loss: 0.064919, val_acc: 24.490889
+Epoch [47], train_loss: 0.063230, val_loss: 0.063949, val_acc: 24.550522
+Epoch [48], train_loss: 0.063107, val_loss: 0.064187, val_acc: 24.493616
+Epoch [49], train_loss: 0.062749, val_loss: 0.063807, val_acc: 24.271498
+Epoch [50], train_loss: 0.062572, val_loss: 0.063802, val_acc: 24.263880
+Epoch [51], train_loss: 0.062300, val_loss: 0.063911, val_acc: 24.351789
+Epoch [52], train_loss: 0.061917, val_loss: 0.063277, val_acc: 24.564375
+Epoch [53], train_loss: 0.061687, val_loss: 0.062791, val_acc: 24.537611
+Epoch [54], train_loss: 0.061547, val_loss: 0.062217, val_acc: 24.649738
+Epoch [55], train_loss: 0.061234, val_loss: 0.062966, val_acc: 24.405647
+Epoch [56], train_loss: 0.061069, val_loss: 0.062621, val_acc: 24.688513
+Epoch [57], train_loss: 0.060774, val_loss: 0.062139, val_acc: 24.681768
+Epoch [58], train_loss: 0.060581, val_loss: 0.063283, val_acc: 24.590117
+Epoch [59], train_loss: 0.060411, val_loss: 0.061419, val_acc: 24.615086
+Epoch [60], train_loss: 0.060230, val_loss: 0.061734, val_acc: 24.515486
+Epoch [61], train_loss: 0.059994, val_loss: 0.061431, val_acc: 24.782021
+Epoch [62], train_loss: 0.059841, val_loss: 0.061522, val_acc: 24.673655
+Epoch [63], train_loss: 0.059629, val_loss: 0.061140, val_acc: 24.692921
+Epoch [64], train_loss: 0.059449, val_loss: 0.061060, val_acc: 24.751156
+Epoch [65], train_loss: 0.059271, val_loss: 0.061181, val_acc: 24.665527
+Epoch [66], train_loss: 0.059026, val_loss: 0.061023, val_acc: 24.630236
+Epoch [67], train_loss: 0.058898, val_loss: 0.061015, val_acc: 24.389702
+Epoch [68], train_loss: 0.058762, val_loss: 0.061788, val_acc: 24.399563
+Epoch [69], train_loss: 0.058593, val_loss: 0.060741, val_acc: 24.468637
+Epoch [70], train_loss: 0.058420, val_loss: 0.060939, val_acc: 24.519287
+Epoch [71], train_loss: 0.058290, val_loss: 0.061458, val_acc: 24.335995
+Epoch [72], train_loss: 0.058148, val_loss: 0.061476, val_acc: 24.577667
+Epoch [73], train_loss: 0.057937, val_loss: 0.060702, val_acc: 24.362522
+Epoch [74], train_loss: 0.057796, val_loss: 0.060193, val_acc: 24.415249
+Epoch [75], train_loss: 0.057669, val_loss: 0.060374, val_acc: 24.400429
+Epoch [76], train_loss: 0.057667, val_loss: 0.060466, val_acc: 24.394871
+Epoch [77], train_loss: 0.057367, val_loss: 0.060432, val_acc: 24.382597
+Epoch [78], train_loss: 0.057320, val_loss: 0.061207, val_acc: 24.174210
+Epoch [79], train_loss: 0.057194, val_loss: 0.061402, val_acc: 24.212704
+Epoch [80], train_loss: 0.057065, val_loss: 0.060596, val_acc: 23.966698
+Epoch [81], train_loss: 0.057184, val_loss: 0.060845, val_acc: 24.160776
+Epoch [82], train_loss: 0.056919, val_loss: 0.060344, val_acc: 24.167057
+Epoch [83], train_loss: 0.056769, val_loss: 0.060171, val_acc: 24.212263
+Epoch [84], train_loss: 0.056629, val_loss: 0.060419, val_acc: 24.140381
+Epoch [85], train_loss: 0.056526, val_loss: 0.060208, val_acc: 24.284134
+Epoch [86], train_loss: 0.056400, val_loss: 0.060158, val_acc: 24.048124
+Epoch [87], train_loss: 0.056368, val_loss: 0.060121, val_acc: 24.221704
+Epoch [88], train_loss: 0.056241, val_loss: 0.060243, val_acc: 23.801796
+Epoch [89], train_loss: 0.056344, val_loss: 0.060374, val_acc: 23.992603
+Epoch [90], train_loss: 0.056528, val_loss: 0.060326, val_acc: 23.967413
+Epoch [91], train_loss: 0.056202, val_loss: 0.060366, val_acc: 24.105375
+Epoch [92], train_loss: 0.056031, val_loss: 0.060369, val_acc: 23.801430
+Epoch [93], train_loss: 0.055863, val_loss: 0.060298, val_acc: 23.932133
+Epoch [94], train_loss: 0.055833, val_loss: 0.060630, val_acc: 23.960375
+Epoch [95], train_loss: 0.055727, val_loss: 0.060611, val_acc: 23.936228
+Epoch [96], train_loss: 0.055719, val_loss: 0.060391, val_acc: 23.530317
+Epoch [97], train_loss: 0.055604, val_loss: 0.060488, val_acc: 23.870846
+Epoch [98], train_loss: 0.055516, val_loss: 0.060361, val_acc: 23.751495
+Epoch [99], train_loss: 0.055485, val_loss: 0.060182, val_acc: 23.912992
+Epoch [100], train_loss: 0.055783, val_loss: 0.060249, val_acc: 23.894049
+Epoch [101], train_loss: 0.055512, val_loss: 0.060705, val_acc: 23.794889
+Epoch [102], train_loss: 0.055448, val_loss: 0.061106, val_acc: 23.843971
+Epoch [103], train_loss: 0.055298, val_loss: 0.060378, val_acc: 23.559891
+Epoch [104], train_loss: 0.055217, val_loss: 0.060069, val_acc: 24.029453
+Epoch [105], train_loss: 0.055107, val_loss: 0.060436, val_acc: 23.739906
+Epoch [106], train_loss: 0.055088, val_loss: 0.060677, val_acc: 23.833448
+Epoch [107], train_loss: 0.055072, val_loss: 0.060842, val_acc: 23.800903
+Epoch [108], train_loss: 0.055009, val_loss: 0.060428, val_acc: 23.687342
+Epoch [109], train_loss: 0.054910, val_loss: 0.060393, val_acc: 23.770208
+Epoch [110], train_loss: 0.054866, val_loss: 0.060454, val_acc: 23.808092
+Epoch [111], train_loss: 0.054774, val_loss: 0.060527, val_acc: 23.613052
+Epoch [112], train_loss: 0.054834, val_loss: 0.060393, val_acc: 23.724047
+Epoch [113], train_loss: 0.054967, val_loss: 0.060046, val_acc: 23.958916
+Epoch [114], train_loss: 0.054710, val_loss: 0.060300, val_acc: 23.646479
+Epoch [115], train_loss: 0.054684, val_loss: 0.060194, val_acc: 23.645292
+Epoch [116], train_loss: 0.054608, val_loss: 0.060591, val_acc: 23.643265
+Epoch [117], train_loss: 0.054572, val_loss: 0.060483, val_acc: 23.554932
+Epoch [118], train_loss: 0.054482, val_loss: 0.060349, val_acc: 23.644648
+Epoch [119], train_loss: 0.054487, val_loss: 0.060369, val_acc: 23.764252
+Epoch [120], train_loss: 0.054343, val_loss: 0.060642, val_acc: 23.431524
+Epoch [121], train_loss: 0.054351, val_loss: 0.060677, val_acc: 23.275038
+Epoch [122], train_loss: 0.054325, val_loss: 0.060439, val_acc: 23.588789
+Epoch [123], train_loss: 0.054208, val_loss: 0.060669, val_acc: 23.548100
+Epoch [124], train_loss: 0.054225, val_loss: 0.060459, val_acc: 23.745020
+Epoch [125], train_loss: 0.054144, val_loss: 0.060477, val_acc: 23.647518
+Epoch [126], train_loss: 0.054115, val_loss: 0.060730, val_acc: 23.275696
+Epoch [127], train_loss: 0.054097, val_loss: 0.060554, val_acc: 23.506828
+Epoch [128], train_loss: 0.054083, val_loss: 0.060776, val_acc: 23.642790
+Epoch [129], train_loss: 0.054086, val_loss: 0.060838, val_acc: 23.461657
+Epoch [130], train_loss: 0.053959, val_loss: 0.060931, val_acc: 23.378143
+Epoch [131], train_loss: 0.053913, val_loss: 0.060576, val_acc: 23.340752
+Epoch [132], train_loss: 0.053883, val_loss: 0.060807, val_acc: 23.445896
+Epoch [133], train_loss: 0.053765, val_loss: 0.060648, val_acc: 23.451881
+Epoch [134], train_loss: 0.053747, val_loss: 0.060545, val_acc: 23.577911
+Epoch [135], train_loss: 0.053737, val_loss: 0.060625, val_acc: 23.530005
+Epoch [136], train_loss: 0.053714, val_loss: 0.060641, val_acc: 23.273563
+Epoch [137], train_loss: 0.053686, val_loss: 0.060768, val_acc: 23.306366
+Epoch [138], train_loss: 0.053599, val_loss: 0.060857, val_acc: 23.298582
+Epoch [139], train_loss: 0.053562, val_loss: 0.060727, val_acc: 23.337814
+Epoch [140], train_loss: 0.053552, val_loss: 0.060808, val_acc: 23.266100
+Epoch [141], train_loss: 0.053531, val_loss: 0.060638, val_acc: 23.482094
+Epoch [142], train_loss: 0.053441, val_loss: 0.060955, val_acc: 22.950975
+Epoch [143], train_loss: 0.053392, val_loss: 0.060695, val_acc: 23.361891
+Epoch [144], train_loss: 0.053365, val_loss: 0.060809, val_acc: 23.293259
+Epoch [145], train_loss: 0.053283, val_loss: 0.060715, val_acc: 23.436928
+Epoch [146], train_loss: 0.053229, val_loss: 0.060929, val_acc: 23.094084
+Epoch [147], train_loss: 0.053267, val_loss: 0.060960, val_acc: 23.204590
+Epoch [148], train_loss: 0.053212, val_loss: 0.060774, val_acc: 23.352613
+Epoch [149], train_loss: 0.053193, val_loss: 0.061320, val_acc: 23.050800
+Epoch [150], train_loss: 0.053150, val_loss: 0.061234, val_acc: 23.131693
+Epoch [151], train_loss: 0.053144, val_loss: 0.060996, val_acc: 23.321447
+Epoch [152], train_loss: 0.053103, val_loss: 0.061014, val_acc: 23.199705
+Epoch [153], train_loss: 0.053013, val_loss: 0.061238, val_acc: 23.175402
+Epoch [154], train_loss: 0.052973, val_loss: 0.061310, val_acc: 23.054157
+Epoch [155], train_loss: 0.052971, val_loss: 0.061006, val_acc: 23.155273
+Epoch [156], train_loss: 0.052924, val_loss: 0.061054, val_acc: 23.097107
+Epoch [157], train_loss: 0.052911, val_loss: 0.061038, val_acc: 23.227934
+Epoch [158], train_loss: 0.052853, val_loss: 0.061200, val_acc: 23.201506
+Epoch [159], train_loss: 0.052853, val_loss: 0.061173, val_acc: 23.052324
+Epoch [160], train_loss: 0.052830, val_loss: 0.061068, val_acc: 23.224878
+Epoch [161], train_loss: 0.052759, val_loss: 0.060999, val_acc: 23.229218
+Epoch [162], train_loss: 0.052736, val_loss: 0.061169, val_acc: 22.908527
+Epoch [163], train_loss: 0.052681, val_loss: 0.060977, val_acc: 23.056473
+Epoch [164], train_loss: 0.052646, val_loss: 0.061263, val_acc: 23.093018
+Epoch [165], train_loss: 0.052617, val_loss: 0.061359, val_acc: 23.012764
+Epoch [166], train_loss: 0.052568, val_loss: 0.060924, val_acc: 23.173973
+Epoch [167], train_loss: 0.052565, val_loss: 0.061263, val_acc: 22.930313
+Epoch [168], train_loss: 0.052476, val_loss: 0.061405, val_acc: 22.924097
+Epoch [169], train_loss: 0.052493, val_loss: 0.061278, val_acc: 22.948893
+Epoch [170], train_loss: 0.052470, val_loss: 0.060960, val_acc: 23.108128
+Epoch [171], train_loss: 0.052441, val_loss: 0.061474, val_acc: 23.134071
+Epoch [172], train_loss: 0.052406, val_loss: 0.061263, val_acc: 22.886589
+Epoch [173], train_loss: 0.052387, val_loss: 0.061368, val_acc: 22.717253
+Epoch [174], train_loss: 0.052312, val_loss: 0.061213, val_acc: 23.041588
+Epoch [175], train_loss: 0.052779, val_loss: 0.061538, val_acc: 22.542048
+Epoch [176], train_loss: 0.052539, val_loss: 0.061570, val_acc: 23.001022
+Epoch [177], train_loss: 0.052411, val_loss: 0.061520, val_acc: 22.884876
+Epoch [178], train_loss: 0.052294, val_loss: 0.061391, val_acc: 23.039955
+Epoch [179], train_loss: 0.052207, val_loss: 0.061321, val_acc: 22.972116
+Epoch [180], train_loss: 0.052229, val_loss: 0.061391, val_acc: 22.941881
+Epoch [181], train_loss: 0.052183, val_loss: 0.061537, val_acc: 22.701088
+Epoch [182], train_loss: 0.052141, val_loss: 0.061517, val_acc: 23.004381
+Epoch [183], train_loss: 0.052104, val_loss: 0.061372, val_acc: 22.875536
+Epoch [184], train_loss: 0.052093, val_loss: 0.061244, val_acc: 23.143198
+Epoch [185], train_loss: 0.052025, val_loss: 0.061398, val_acc: 22.850655
+Epoch [186], train_loss: 0.052035, val_loss: 0.061165, val_acc: 22.970526
+Epoch [187], train_loss: 0.051996, val_loss: 0.061186, val_acc: 23.001593
+Epoch [188], train_loss: 0.051923, val_loss: 0.061167, val_acc: 23.013222
+Epoch [189], train_loss: 0.051924, val_loss: 0.061888, val_acc: 22.720547
+Epoch [190], train_loss: 0.051946, val_loss: 0.061504, val_acc: 22.894875
+Epoch [191], train_loss: 0.051904, val_loss: 0.062099, val_acc: 22.526489
+Epoch [192], train_loss: 0.051862, val_loss: 0.061550, val_acc: 22.830462
+Epoch [193], train_loss: 0.052044, val_loss: 0.061732, val_acc: 22.850498
+Epoch [194], train_loss: 0.051970, val_loss: 0.061430, val_acc: 22.810593
+Epoch [195], train_loss: 0.051840, val_loss: 0.061349, val_acc: 22.843336
+Epoch [196], train_loss: 0.051772, val_loss: 0.061576, val_acc: 22.800817
+Epoch [197], train_loss: 0.051763, val_loss: 0.061528, val_acc: 22.789726
+Epoch [198], train_loss: 0.051702, val_loss: 0.061500, val_acc: 22.814890
+Epoch [199], train_loss: 0.051683, val_loss: 0.061516, val_acc: 22.714888
+Epoch [200], train_loss: 0.051661, val_loss: 0.061390, val_acc: 22.990637
+Epoch [201], train_loss: 0.051646, val_loss: 0.061659, val_acc: 22.731455
+Epoch [202], train_loss: 0.051635, val_loss: 0.061766, val_acc: 22.724146
+Epoch [203], train_loss: 0.051579, val_loss: 0.061717, val_acc: 22.806280
+Epoch [204], train_loss: 0.051579, val_loss: 0.061682, val_acc: 22.852608
+Epoch [205], train_loss: 0.051517, val_loss: 0.061574, val_acc: 22.776537
+Epoch [206], train_loss: 0.051491, val_loss: 0.061710, val_acc: 22.826565
+Epoch [207], train_loss: 0.051514, val_loss: 0.061837, val_acc: 22.544420
+Epoch [208], train_loss: 0.051475, val_loss: 0.061875, val_acc: 22.581282
+Epoch [209], train_loss: 0.051456, val_loss: 0.061608, val_acc: 22.789347
+Epoch [210], train_loss: 0.051395, val_loss: 0.061499, val_acc: 22.844645
+Epoch [211], train_loss: 0.051398, val_loss: 0.061666, val_acc: 22.603065
+Epoch [212], train_loss: 0.051386, val_loss: 0.061633, val_acc: 22.725840
+Epoch [213], train_loss: 0.051366, val_loss: 0.061487, val_acc: 22.797012
+Epoch [214], train_loss: 0.051286, val_loss: 0.061715, val_acc: 22.697880
+Epoch [215], train_loss: 0.051220, val_loss: 0.061821, val_acc: 22.700386
+Epoch [216], train_loss: 0.051277, val_loss: 0.061954, val_acc: 22.758692
+Epoch [217], train_loss: 0.051235, val_loss: 0.061676, val_acc: 22.724503
+Epoch [218], train_loss: 0.051256, val_loss: 0.061804, val_acc: 22.682705
+Epoch [219], train_loss: 0.051248, val_loss: 0.061638, val_acc: 22.797997
+Epoch [220], train_loss: 0.051228, val_loss: 0.061666, val_acc: 22.822092
+Epoch [221], train_loss: 0.051135, val_loss: 0.061788, val_acc: 22.788258
+Epoch [222], train_loss: 0.051098, val_loss: 0.061827, val_acc: 22.737278
+Epoch [223], train_loss: 0.051074, val_loss: 0.061775, val_acc: 22.523264
+Epoch [224], train_loss: 0.051092, val_loss: 0.061672, val_acc: 22.681999
+Epoch [225], train_loss: 0.051070, val_loss: 0.061953, val_acc: 22.691309
+Epoch [226], train_loss: 0.051027, val_loss: 0.062038, val_acc: 22.556974
+Epoch [227], train_loss: 0.051009, val_loss: 0.061850, val_acc: 22.708612
+Epoch [228], train_loss: 0.050986, val_loss: 0.061746, val_acc: 22.628260
+Epoch [229], train_loss: 0.050954, val_loss: 0.061939, val_acc: 22.605965
+Epoch [230], train_loss: 0.050974, val_loss: 0.061693, val_acc: 22.797508
+Epoch [231], train_loss: 0.050932, val_loss: 0.061837, val_acc: 22.720713
+Epoch [232], train_loss: 0.050928, val_loss: 0.061774, val_acc: 22.709238
+Epoch [233], train_loss: 0.050834, val_loss: 0.061915, val_acc: 22.793716
+Epoch [234], train_loss: 0.050889, val_loss: 0.062004, val_acc: 22.601929
+Epoch [235], train_loss: 0.050864, val_loss: 0.062182, val_acc: 22.514433
+Epoch [236], train_loss: 0.050840, val_loss: 0.061956, val_acc: 22.620174
+Epoch [237], train_loss: 0.050805, val_loss: 0.061769, val_acc: 22.829742
+Epoch [238], train_loss: 0.050796, val_loss: 0.062186, val_acc: 22.528975
+Epoch [239], train_loss: 0.050741, val_loss: 0.062236, val_acc: 22.477934
+Epoch [240], train_loss: 0.050787, val_loss: 0.062033, val_acc: 22.596165
+Epoch [241], train_loss: 0.050723, val_loss: 0.062612, val_acc: 22.367857
+Epoch [242], train_loss: 0.050766, val_loss: 0.061872, val_acc: 22.674738
+Epoch [243], train_loss: 0.050683, val_loss: 0.062485, val_acc: 22.384010
+Epoch [244], train_loss: 0.050679, val_loss: 0.062159, val_acc: 22.512274
+Epoch [245], train_loss: 0.050675, val_loss: 0.061834, val_acc: 22.704323
+Epoch [246], train_loss: 0.050789, val_loss: 0.062112, val_acc: 22.833523
+Epoch [247], train_loss: 0.051153, val_loss: 0.062049, val_acc: 22.613068
+Epoch [248], train_loss: 0.050777, val_loss: 0.062078, val_acc: 22.681463
+Epoch [249], train_loss: 0.050664, val_loss: 0.062420, val_acc: 22.475418
+Epoch [250], train_loss: 0.050610, val_loss: 0.062049, val_acc: 22.602955
+Epoch [251], train_loss: 0.050568, val_loss: 0.062036, val_acc: 22.734924
+Epoch [252], train_loss: 0.050525, val_loss: 0.062149, val_acc: 22.465708
+Epoch [253], train_loss: 0.050459, val_loss: 0.062127, val_acc: 22.559071
+Epoch [254], train_loss: 0.050456, val_loss: 0.062235, val_acc: 22.477964
+Epoch [255], train_loss: 0.050401, val_loss: 0.062209, val_acc: 22.425743
+Epoch [256], train_loss: 0.050449, val_loss: 0.062403, val_acc: 22.588591
+Epoch [257], train_loss: 0.050412, val_loss: 0.062021, val_acc: 22.730080
+Epoch [258], train_loss: 0.050414, val_loss: 0.062177, val_acc: 22.621742
+Epoch [259], train_loss: 0.050399, val_loss: 0.062278, val_acc: 22.536293
+Epoch [260], train_loss: 0.050341, val_loss: 0.062265, val_acc: 22.602362
+Epoch [261], train_loss: 0.050357, val_loss: 0.061851, val_acc: 22.766645
+Epoch [262], train_loss: 0.050312, val_loss: 0.062039, val_acc: 22.642006
+Epoch [263], train_loss: 0.050367, val_loss: 0.062593, val_acc: 22.288824
+Epoch [264], train_loss: 0.050292, val_loss: 0.062336, val_acc: 22.536591
+Epoch [265], train_loss: 0.050290, val_loss: 0.062562, val_acc: 22.546824
+Epoch [266], train_loss: 0.050265, val_loss: 0.062284, val_acc: 22.549255
+Epoch [267], train_loss: 0.050258, val_loss: 0.062322, val_acc: 22.469826
+Epoch [268], train_loss: 0.050212, val_loss: 0.062271, val_acc: 22.602158
+Epoch [269], train_loss: 0.050236, val_loss: 0.062315, val_acc: 22.475492
+Epoch [270], train_loss: 0.050265, val_loss: 0.062536, val_acc: 22.369736
+Epoch [271], train_loss: 0.050197, val_loss: 0.062399, val_acc: 22.407486
+Epoch [272], train_loss: 0.050126, val_loss: 0.062486, val_acc: 22.368320
+Epoch [273], train_loss: 0.050148, val_loss: 0.062338, val_acc: 22.512203
+Epoch [274], train_loss: 0.050068, val_loss: 0.062304, val_acc: 22.586666
+Epoch [275], train_loss: 0.050095, val_loss: 0.062585, val_acc: 22.271826
+Epoch [276], train_loss: 0.050053, val_loss: 0.062300, val_acc: 22.611076
+Epoch [277], train_loss: 0.050822, val_loss: 0.062574, val_acc: 22.386127
+Epoch [278], train_loss: 0.051561, val_loss: 0.062073, val_acc: 22.665815
+Epoch [279], train_loss: 0.050725, val_loss: 0.062053, val_acc: 22.617510
+Epoch [280], train_loss: 0.050410, val_loss: 0.061900, val_acc: 22.656696
+Epoch [281], train_loss: 0.050261, val_loss: 0.062333, val_acc: 22.404108
+Epoch [282], train_loss: 0.050170, val_loss: 0.062242, val_acc: 22.602995
+Epoch [283], train_loss: 0.050151, val_loss: 0.062393, val_acc: 22.483303
+Epoch [284], train_loss: 0.050088, val_loss: 0.062337, val_acc: 22.479488
+Epoch [285], train_loss: 0.050055, val_loss: 0.062338, val_acc: 22.527645
+Epoch [286], train_loss: 0.050020, val_loss: 0.062342, val_acc: 22.561609
+Epoch [287], train_loss: 0.050008, val_loss: 0.062216, val_acc: 22.482193
+Epoch [288], train_loss: 0.049981, val_loss: 0.062552, val_acc: 22.463575
+Epoch [289], train_loss: 0.049953, val_loss: 0.062537, val_acc: 22.366322
+Epoch [290], train_loss: 0.049930, val_loss: 0.062416, val_acc: 22.557228
+Epoch [291], train_loss: 0.049908, val_loss: 0.062540, val_acc: 22.318214
+Epoch [292], train_loss: 0.049894, val_loss: 0.062419, val_acc: 22.563217
+Epoch [293], train_loss: 0.049874, val_loss: 0.062457, val_acc: 22.543566
+Epoch [294], train_loss: 0.049866, val_loss: 0.062526, val_acc: 22.384052
+Epoch [295], train_loss: 0.049851, val_loss: 0.062701, val_acc: 22.416592
+Epoch [296], train_loss: 0.049841, val_loss: 0.062489, val_acc: 22.503382
+Epoch [297], train_loss: 0.049869, val_loss: 0.062571, val_acc: 22.355141
+Epoch [298], train_loss: 0.049859, val_loss: 0.062496, val_acc: 22.513489
+Epoch [299], train_loss: 0.049886, val_loss: 0.062456, val_acc: 22.400202
+Epoch [300], train_loss: 0.049818, val_loss: 0.062634, val_acc: 22.308228
+Epoch [301], train_loss: 0.049806, val_loss: 0.062367, val_acc: 22.514076
+Epoch [302], train_loss: 0.049750, val_loss: 0.062724, val_acc: 22.339508
+Epoch [303], train_loss: 0.049726, val_loss: 0.062564, val_acc: 22.536779
+Epoch [304], train_loss: 0.049753, val_loss: 0.062532, val_acc: 22.518066
+Epoch [305], train_loss: 0.049714, val_loss: 0.062484, val_acc: 22.405741
+Epoch [306], train_loss: 0.049758, val_loss: 0.062720, val_acc: 22.276119
+Epoch [307], train_loss: 0.049730, val_loss: 0.062580, val_acc: 22.449997
+Epoch [308], train_loss: 0.049702, val_loss: 0.062844, val_acc: 22.208313
+Epoch [309], train_loss: 0.049630, val_loss: 0.062686, val_acc: 22.339739
+Epoch [310], train_loss: 0.049684, val_loss: 0.062507, val_acc: 22.495686
+Epoch [311], train_loss: 0.049644, val_loss: 0.062787, val_acc: 22.337009
+Epoch [312], train_loss: 0.049623, val_loss: 0.062539, val_acc: 22.568995
+Epoch [313], train_loss: 0.049601, val_loss: 0.062533, val_acc: 22.360870
+Epoch [314], train_loss: 0.049603, val_loss: 0.062691, val_acc: 22.418070
+Epoch [315], train_loss: 0.049572, val_loss: 0.062746, val_acc: 22.334587
+Epoch [316], train_loss: 0.049574, val_loss: 0.062683, val_acc: 22.355537
+Epoch [317], train_loss: 0.049571, val_loss: 0.062952, val_acc: 22.116482
+Epoch [318], train_loss: 0.049547, val_loss: 0.062516, val_acc: 22.455540
+Epoch [319], train_loss: 0.049502, val_loss: 0.062459, val_acc: 22.479536
+Epoch [320], train_loss: 0.049482, val_loss: 0.062791, val_acc: 22.485613
+Epoch [321], train_loss: 0.049461, val_loss: 0.062690, val_acc: 22.390081
+Epoch [322], train_loss: 0.049432, val_loss: 0.062730, val_acc: 22.289698
+Epoch [323], train_loss: 0.049422, val_loss: 0.062708, val_acc: 22.397993
+Epoch [324], train_loss: 0.049470, val_loss: 0.062796, val_acc: 22.361925
+Epoch [325], train_loss: 0.049442, val_loss: 0.062792, val_acc: 22.377131
+Epoch [326], train_loss: 0.049423, val_loss: 0.062720, val_acc: 22.372772
+Epoch [327], train_loss: 0.049426, val_loss: 0.062722, val_acc: 22.439816
+Epoch [328], train_loss: 0.049388, val_loss: 0.062701, val_acc: 22.308943
+Epoch [329], train_loss: 0.049356, val_loss: 0.062839, val_acc: 22.338873
+Epoch [330], train_loss: 0.049373, val_loss: 0.063103, val_acc: 22.164068
+Epoch [331], train_loss: 0.049383, val_loss: 0.062873, val_acc: 22.398132
+Epoch [332], train_loss: 0.049383, val_loss: 0.062917, val_acc: 22.320862
+Epoch [333], train_loss: 0.049312, val_loss: 0.063128, val_acc: 22.240221
+Epoch [334], train_loss: 0.049330, val_loss: 0.063016, val_acc: 22.207783
+Epoch [335], train_loss: 0.049254, val_loss: 0.063016, val_acc: 22.290277
+Epoch [336], train_loss: 0.049253, val_loss: 0.062824, val_acc: 22.498003
+Epoch [337], train_loss: 0.049235, val_loss: 0.062786, val_acc: 22.465691
+Epoch [338], train_loss: 0.049236, val_loss: 0.062594, val_acc: 22.557634
+Epoch [339], train_loss: 0.049276, val_loss: 0.062807, val_acc: 22.366901
+Epoch [340], train_loss: 0.049261, val_loss: 0.063243, val_acc: 22.044468
+Epoch [341], train_loss: 0.049250, val_loss: 0.062809, val_acc: 22.398554
+Epoch [342], train_loss: 0.049227, val_loss: 0.063055, val_acc: 22.295439
+Epoch [343], train_loss: 0.049231, val_loss: 0.063406, val_acc: 22.200113
+Epoch [344], train_loss: 0.049341, val_loss: 0.062640, val_acc: 22.520212
+Epoch [345], train_loss: 0.049172, val_loss: 0.062983, val_acc: 22.383247
+Epoch [346], train_loss: 0.049155, val_loss: 0.062845, val_acc: 22.413303
+Epoch [347], train_loss: 0.049166, val_loss: 0.062850, val_acc: 22.395575
+Epoch [348], train_loss: 0.049163, val_loss: 0.062984, val_acc: 22.290829
+Epoch [349], train_loss: 0.049154, val_loss: 0.063024, val_acc: 22.303303
+Epoch [350], train_loss: 0.049103, val_loss: 0.063282, val_acc: 22.142099
+Epoch [351], train_loss: 0.049109, val_loss: 0.063160, val_acc: 22.231277
+Epoch [352], train_loss: 0.049076, val_loss: 0.063326, val_acc: 22.092487
+Epoch [353], train_loss: 0.049095, val_loss: 0.062948, val_acc: 22.356733
+Epoch [354], train_loss: 0.049039, val_loss: 0.062953, val_acc: 22.412064
+Epoch [355], train_loss: 0.049026, val_loss: 0.062696, val_acc: 22.451530
+Epoch [356], train_loss: 0.049032, val_loss: 0.062971, val_acc: 22.315907
+Epoch [357], train_loss: 0.049036, val_loss: 0.063294, val_acc: 22.344683
+Epoch [358], train_loss: 0.049016, val_loss: 0.062708, val_acc: 22.576414
+Epoch [359], train_loss: 0.049044, val_loss: 0.063032, val_acc: 22.351780
+Epoch [360], train_loss: 0.048920, val_loss: 0.063081, val_acc: 22.240406
+Epoch [361], train_loss: 0.048945, val_loss: 0.063378, val_acc: 21.997189
+Epoch [362], train_loss: 0.049009, val_loss: 0.062809, val_acc: 22.382597
+Epoch [363], train_loss: 0.048944, val_loss: 0.063189, val_acc: 22.238960
+Epoch [364], train_loss: 0.048904, val_loss: 0.062875, val_acc: 22.432976
+Epoch [365], train_loss: 0.048896, val_loss: 0.063052, val_acc: 22.342827
+Epoch [366], train_loss: 0.048901, val_loss: 0.063552, val_acc: 22.000128
+Epoch [367], train_loss: 0.048884, val_loss: 0.063204, val_acc: 22.291206
+Epoch [368], train_loss: 0.048882, val_loss: 0.063163, val_acc: 22.311848
+Epoch [369], train_loss: 0.048866, val_loss: 0.063421, val_acc: 22.241776
+Epoch [370], train_loss: 0.048874, val_loss: 0.063123, val_acc: 22.191980
+Epoch [371], train_loss: 0.048864, val_loss: 0.063163, val_acc: 22.172377
+Epoch [372], train_loss: 0.048776, val_loss: 0.063314, val_acc: 22.201338
+Epoch [373], train_loss: 0.048830, val_loss: 0.063173, val_acc: 22.186214
+Epoch [374], train_loss: 0.048842, val_loss: 0.063265, val_acc: 22.344231
+Epoch [375], train_loss: 0.048745, val_loss: 0.063163, val_acc: 22.266041
+Epoch [376], train_loss: 0.048778, val_loss: 0.063388, val_acc: 22.088840
+Epoch [377], train_loss: 0.048727, val_loss: 0.063203, val_acc: 22.154692
+Epoch [378], train_loss: 0.048748, val_loss: 0.063363, val_acc: 22.299435
+Epoch [379], train_loss: 0.048761, val_loss: 0.063148, val_acc: 22.410744
+Epoch [380], train_loss: 0.048677, val_loss: 0.063310, val_acc: 22.209721
+Epoch [381], train_loss: 0.048693, val_loss: 0.063379, val_acc: 22.178541
+Epoch [382], train_loss: 0.048719, val_loss: 0.063271, val_acc: 22.206450
+Epoch [383], train_loss: 0.048700, val_loss: 0.063574, val_acc: 22.189806
+Epoch [384], train_loss: 0.048719, val_loss: 0.063422, val_acc: 22.248947
+Epoch [385], train_loss: 0.048661, val_loss: 0.063531, val_acc: 22.029692
+Epoch [386], train_loss: 0.048653, val_loss: 0.063050, val_acc: 22.288496
+Epoch [387], train_loss: 0.048638, val_loss: 0.063302, val_acc: 22.265503
+Epoch [388], train_loss: 0.048623, val_loss: 0.063038, val_acc: 22.388475
+Epoch [389], train_loss: 0.048610, val_loss: 0.063682, val_acc: 22.060585
+Epoch [390], train_loss: 0.048568, val_loss: 0.063570, val_acc: 21.893202
+Epoch [391], train_loss: 0.048553, val_loss: 0.063450, val_acc: 22.234413
+Epoch [392], train_loss: 0.048542, val_loss: 0.063171, val_acc: 22.338253
+Epoch [393], train_loss: 0.048555, val_loss: 0.062979, val_acc: 22.329920
+Epoch [394], train_loss: 0.048588, val_loss: 0.063308, val_acc: 22.254086
+Epoch [395], train_loss: 0.048538, val_loss: 0.063382, val_acc: 22.120951
+Epoch [396], train_loss: 0.048555, val_loss: 0.063210, val_acc: 22.296587
+Epoch [397], train_loss: 0.048521, val_loss: 0.063364, val_acc: 22.175053
+Epoch [398], train_loss: 0.048468, val_loss: 0.063237, val_acc: 22.231136
+Epoch [399], train_loss: 0.048455, val_loss: 0.063274, val_acc: 22.301725
+Epoch [400], train_loss: 0.048493, val_loss: 0.063468, val_acc: 22.303627
+Epoch [401], train_loss: 0.048466, val_loss: 0.063465, val_acc: 22.103638
+Epoch [402], train_loss: 0.048489, val_loss: 0.063594, val_acc: 22.184689
+Epoch [403], train_loss: 0.048491, val_loss: 0.063267, val_acc: 22.255508
+Epoch [404], train_loss: 0.048476, val_loss: 0.063461, val_acc: 22.225859
+Epoch [405], train_loss: 0.048408, val_loss: 0.063543, val_acc: 22.126499
+Epoch [406], train_loss: 0.048358, val_loss: 0.063357, val_acc: 22.269449
+Epoch [407], train_loss: 0.048409, val_loss: 0.063821, val_acc: 22.013691
+Epoch [408], train_loss: 0.048368, val_loss: 0.063235, val_acc: 22.399445
+Epoch [409], train_loss: 0.048406, val_loss: 0.063636, val_acc: 22.129269
+Epoch [410], train_loss: 0.048319, val_loss: 0.063719, val_acc: 22.074171
+Epoch [411], train_loss: 0.048345, val_loss: 0.063613, val_acc: 22.129536
+Epoch [412], train_loss: 0.048357, val_loss: 0.063695, val_acc: 22.059387
+Epoch [413], train_loss: 0.048363, val_loss: 0.063419, val_acc: 22.187750
+Epoch [414], train_loss: 0.048335, val_loss: 0.063410, val_acc: 22.233442
+Epoch [415], train_loss: 0.048341, val_loss: 0.063667, val_acc: 22.090216
+Epoch [416], train_loss: 0.048314, val_loss: 0.063611, val_acc: 22.103971
+Epoch [417], train_loss: 0.048271, val_loss: 0.063421, val_acc: 22.279119
+Epoch [418], train_loss: 0.048205, val_loss: 0.063680, val_acc: 22.098957
+Epoch [419], train_loss: 0.048267, val_loss: 0.063485, val_acc: 22.181131
+Epoch [420], train_loss: 0.048329, val_loss: 0.063459, val_acc: 22.220982
+Epoch [421], train_loss: 0.048255, val_loss: 0.063517, val_acc: 22.135687
+Epoch [422], train_loss: 0.048169, val_loss: 0.063796, val_acc: 22.039988
+Epoch [423], train_loss: 0.048190, val_loss: 0.063494, val_acc: 22.167435
+Epoch [424], train_loss: 0.048360, val_loss: 0.063166, val_acc: 22.337254
+Epoch [425], train_loss: 0.048228, val_loss: 0.063758, val_acc: 22.091017
+Epoch [426], train_loss: 0.048200, val_loss: 0.063714, val_acc: 22.118862
+Epoch [427], train_loss: 0.048211, val_loss: 0.063492, val_acc: 22.201731
+Epoch [428], train_loss: 0.048237, val_loss: 0.063553, val_acc: 22.264580
+Epoch [429], train_loss: 0.048163, val_loss: 0.063809, val_acc: 22.101276
+Epoch [430], train_loss: 0.048154, val_loss: 0.063486, val_acc: 22.241615
+Epoch [431], train_loss: 0.048135, val_loss: 0.063782, val_acc: 22.021601
+Epoch [432], train_loss: 0.048154, val_loss: 0.064108, val_acc: 21.937464
+Epoch [433], train_loss: 0.048127, val_loss: 0.063317, val_acc: 22.343370
+Epoch [434], train_loss: 0.048160, val_loss: 0.063822, val_acc: 22.126307
+Epoch [435], train_loss: 0.048059, val_loss: 0.063655, val_acc: 22.239500
+Epoch [436], train_loss: 0.048098, val_loss: 0.063292, val_acc: 22.311499
+Epoch [437], train_loss: 0.048087, val_loss: 0.063696, val_acc: 22.182224
+Epoch [438], train_loss: 0.048059, val_loss: 0.063630, val_acc: 22.237732
+Epoch [439], train_loss: 0.048041, val_loss: 0.063732, val_acc: 22.137695
+Epoch [440], train_loss: 0.048015, val_loss: 0.064030, val_acc: 21.923435
+Epoch [441], train_loss: 0.048094, val_loss: 0.063422, val_acc: 22.274504
+Epoch [442], train_loss: 0.047964, val_loss: 0.063729, val_acc: 22.142748
+Epoch [443], train_loss: 0.048098, val_loss: 0.063879, val_acc: 21.992958
+Epoch [444], train_loss: 0.048060, val_loss: 0.063779, val_acc: 22.150984
+Epoch [445], train_loss: 0.047980, val_loss: 0.063451, val_acc: 22.229000
+Epoch [446], train_loss: 0.047960, val_loss: 0.063607, val_acc: 22.184078
+Epoch [447], train_loss: 0.047935, val_loss: 0.063996, val_acc: 21.849291
+Epoch [448], train_loss: 0.047933, val_loss: 0.063694, val_acc: 22.152288
+Epoch [449], train_loss: 0.047955, val_loss: 0.063809, val_acc: 22.156931
+Epoch [450], train_loss: 0.047961, val_loss: 0.063833, val_acc: 22.148504
+Epoch [451], train_loss: 0.047957, val_loss: 0.063707, val_acc: 22.208931
+Epoch [452], train_loss: 0.047922, val_loss: 0.063996, val_acc: 21.918528
+Epoch [453], train_loss: 0.047898, val_loss: 0.063661, val_acc: 22.153763
+Epoch [454], train_loss: 0.047872, val_loss: 0.063571, val_acc: 22.321342
+Epoch [455], train_loss: 0.047895, val_loss: 0.063599, val_acc: 22.170124
+Epoch [456], train_loss: 0.047866, val_loss: 0.063814, val_acc: 22.175676
+Epoch [457], train_loss: 0.047857, val_loss: 0.063431, val_acc: 22.311750
+Epoch [458], train_loss: 0.047899, val_loss: 0.063873, val_acc: 22.022701
+Epoch [459], train_loss: 0.047949, val_loss: 0.063929, val_acc: 22.081783
+Epoch [460], train_loss: 0.047834, val_loss: 0.063716, val_acc: 22.222347
+Epoch [461], train_loss: 0.047878, val_loss: 0.063864, val_acc: 22.058508
+Epoch [462], train_loss: 0.047814, val_loss: 0.063534, val_acc: 22.269951
+Epoch [463], train_loss: 0.047790, val_loss: 0.063471, val_acc: 22.231197
+Epoch [464], train_loss: 0.047816, val_loss: 0.063979, val_acc: 22.030787
+Epoch [465], train_loss: 0.047802, val_loss: 0.064037, val_acc: 22.017969
+Epoch [466], train_loss: 0.047873, val_loss: 0.064135, val_acc: 21.976042
+Epoch [467], train_loss: 0.047807, val_loss: 0.063842, val_acc: 22.163364
+Epoch [468], train_loss: 0.047757, val_loss: 0.063991, val_acc: 22.047916
+Epoch [469], train_loss: 0.047781, val_loss: 0.063899, val_acc: 22.117508
+Epoch [470], train_loss: 0.047750, val_loss: 0.063940, val_acc: 22.058220
+Epoch [471], train_loss: 0.047728, val_loss: 0.063987, val_acc: 22.074345
+Epoch [472], train_loss: 0.047762, val_loss: 0.063871, val_acc: 22.041473
+Epoch [473], train_loss: 0.047736, val_loss: 0.064080, val_acc: 22.011335
+Epoch [474], train_loss: 0.047735, val_loss: 0.064142, val_acc: 21.922129
+Epoch [475], train_loss: 0.047769, val_loss: 0.063993, val_acc: 21.983545
+Epoch [476], train_loss: 0.047716, val_loss: 0.064023, val_acc: 22.068115
+Epoch [477], train_loss: 0.047680, val_loss: 0.063958, val_acc: 22.042847
+Epoch [478], train_loss: 0.047616, val_loss: 0.064028, val_acc: 22.057844
+Epoch [479], train_loss: 0.047663, val_loss: 0.063870, val_acc: 22.119822
+Epoch [480], train_loss: 0.047629, val_loss: 0.064166, val_acc: 21.982090
+Epoch [481], train_loss: 0.047709, val_loss: 0.064119, val_acc: 21.946262
+Epoch [482], train_loss: 0.047624, val_loss: 0.063704, val_acc: 22.206902
+Epoch [483], train_loss: 0.047672, val_loss: 0.064056, val_acc: 22.034794
+Epoch [484], train_loss: 0.047583, val_loss: 0.064009, val_acc: 22.059017
+Epoch [485], train_loss: 0.047586, val_loss: 0.064082, val_acc: 22.001949
+Epoch [486], train_loss: 0.047621, val_loss: 0.063787, val_acc: 22.263199
+Epoch [487], train_loss: 0.047637, val_loss: 0.063819, val_acc: 22.172937
+Epoch [488], train_loss: 0.047608, val_loss: 0.063948, val_acc: 22.089308
+Epoch [489], train_loss: 0.047608, val_loss: 0.063898, val_acc: 22.140411
+Epoch [490], train_loss: 0.047589, val_loss: 0.064037, val_acc: 22.085833
+Epoch [491], train_loss: 0.047640, val_loss: 0.064350, val_acc: 21.877132
+Epoch [492], train_loss: 0.047539, val_loss: 0.063778, val_acc: 22.298557
+Epoch [493], train_loss: 0.047544, val_loss: 0.064065, val_acc: 22.064720
+Epoch [494], train_loss: 0.047549, val_loss: 0.064179, val_acc: 22.031548
+Epoch [495], train_loss: 0.047604, val_loss: 0.064206, val_acc: 22.007929
+Epoch [496], train_loss: 0.047545, val_loss: 0.063910, val_acc: 22.110052
+Epoch [497], train_loss: 0.047467, val_loss: 0.063998, val_acc: 22.098913
+Epoch [498], train_loss: 0.047502, val_loss: 0.063878, val_acc: 22.101131
+Epoch [499], train_loss: 0.047499, val_loss: 0.064113, val_acc: 22.059759
+python3 ./UNet_V9_3.py  3555.95s user 3208.47s system 99% cpu 1:53:00.07 total
 number auf epochs: 500
 batchsize: 32
 learning rate: 1e-05
 kernel size is: 5
  seed is: 2193910023
-Traceback (most recent call last):
-  File "./UNet_V10.py", line 243, in <module>
-    normalization = np.load(f'{path_to_rep}/UNet/Trainingsdata/Norm_min_max_32_angles.npy')
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/npyio.py", line 441, in load
-    pickle_kwargs=pickle_kwargs)
-  File "/rwthfs/rz/SW/UTIL.common/Python/3.7.11/x86_64/lib/python3.7/site-packages/numpy/lib/format.py", line 743, in read_array
-    raise ValueError("Object arrays cannot be loaded when "
-ValueError: Object arrays cannot be loaded when allow_pickle=False
-python3 ./UNet_V10.py  0.86s user 1.38s system 79% cpu 2.806 total
+Epoch [0], train_loss: 0.200420, val_loss: 0.177010, val_acc: 5.227643
+Epoch [1], train_loss: 0.192670, val_loss: 0.180030, val_acc: 7.121324
+Epoch [2], train_loss: 0.186863, val_loss: 0.184720, val_acc: 7.350025
+Epoch [3], train_loss: 0.182218, val_loss: 0.180996, val_acc: 7.816835
+Epoch [4], train_loss: 0.177794, val_loss: 0.177973, val_acc: 8.309507
+Epoch [5], train_loss: 0.172711, val_loss: 0.172482, val_acc: 9.017692
+Epoch [6], train_loss: 0.166484, val_loss: 0.166277, val_acc: 9.856530
+Epoch [7], train_loss: 0.159429, val_loss: 0.158203, val_acc: 10.751143
+Epoch [8], train_loss: 0.152489, val_loss: 0.149408, val_acc: 11.662172
+Epoch [9], train_loss: 0.146228, val_loss: 0.145681, val_acc: 12.201270
+Epoch [10], train_loss: 0.141337, val_loss: 0.140914, val_acc: 12.710280
+Epoch [11], train_loss: 0.137612, val_loss: 0.135376, val_acc: 13.212721
+Epoch [12], train_loss: 0.134796, val_loss: 0.134232, val_acc: 13.428489
+Epoch [13], train_loss: 0.132420, val_loss: 0.133076, val_acc: 13.601575
+Epoch [14], train_loss: 0.130350, val_loss: 0.131198, val_acc: 13.924735
+Epoch [15], train_loss: 0.128509, val_loss: 0.129329, val_acc: 14.130562
+Epoch [16], train_loss: 0.126831, val_loss: 0.127061, val_acc: 14.429761
+Epoch [17], train_loss: 0.125218, val_loss: 0.125852, val_acc: 14.677369
+Epoch [18], train_loss: 0.123711, val_loss: 0.123066, val_acc: 14.804510
+Epoch [19], train_loss: 0.122309, val_loss: 0.121274, val_acc: 15.107693
+Epoch [20], train_loss: 0.120894, val_loss: 0.120297, val_acc: 15.145585
+Epoch [21], train_loss: 0.119530, val_loss: 0.118137, val_acc: 15.544833
+Epoch [22], train_loss: 0.118205, val_loss: 0.119122, val_acc: 15.619372
+Epoch [23], train_loss: 0.117027, val_loss: 0.115053, val_acc: 15.982980
+Epoch [24], train_loss: 0.115899, val_loss: 0.115951, val_acc: 15.912832
+Epoch [25], train_loss: 0.114858, val_loss: 0.115326, val_acc: 16.154057
+Epoch [26], train_loss: 0.113769, val_loss: 0.110591, val_acc: 16.614986
+Epoch [27], train_loss: 0.112765, val_loss: 0.112326, val_acc: 16.442030
+Epoch [28], train_loss: 0.111757, val_loss: 0.111778, val_acc: 16.515799
+Epoch [29], train_loss: 0.110807, val_loss: 0.109941, val_acc: 16.767067
+Epoch [30], train_loss: 0.109889, val_loss: 0.108325, val_acc: 16.883240
+Epoch [31], train_loss: 0.109004, val_loss: 0.108544, val_acc: 17.000015
+Epoch [32], train_loss: 0.108117, val_loss: 0.107888, val_acc: 17.167463
+Epoch [33], train_loss: 0.107309, val_loss: 0.105782, val_acc: 17.402439
+Epoch [34], train_loss: 0.106488, val_loss: 0.106283, val_acc: 17.375620
+Epoch [35], train_loss: 0.105681, val_loss: 0.104324, val_acc: 17.692352
+Epoch [36], train_loss: 0.104857, val_loss: 0.103980, val_acc: 17.887939
+Epoch [37], train_loss: 0.104042, val_loss: 0.103632, val_acc: 17.698729
+Epoch [38], train_loss: 0.103280, val_loss: 0.102483, val_acc: 17.966345
+Epoch [39], train_loss: 0.102497, val_loss: 0.101482, val_acc: 18.157980
+Epoch [40], train_loss: 0.101758, val_loss: 0.100404, val_acc: 18.566359
+Epoch [41], train_loss: 0.101066, val_loss: 0.101425, val_acc: 18.211044
+Epoch [42], train_loss: 0.100260, val_loss: 0.099332, val_acc: 18.532598
+Epoch [43], train_loss: 0.099637, val_loss: 0.098474, val_acc: 18.736525
+Epoch [44], train_loss: 0.098928, val_loss: 0.099405, val_acc: 18.548424
+Epoch [45], train_loss: 0.098282, val_loss: 0.096814, val_acc: 18.896193
+Epoch [46], train_loss: 0.097613, val_loss: 0.096518, val_acc: 18.995045
+Epoch [47], train_loss: 0.096993, val_loss: 0.094432, val_acc: 19.152565
+Epoch [48], train_loss: 0.096400, val_loss: 0.094221, val_acc: 19.308622
+Epoch [49], train_loss: 0.095806, val_loss: 0.096152, val_acc: 18.937071
+Epoch [50], train_loss: 0.095203, val_loss: 0.094975, val_acc: 19.304646
+Epoch [51], train_loss: 0.094614, val_loss: 0.093499, val_acc: 19.518486
+Epoch [52], train_loss: 0.094125, val_loss: 0.093979, val_acc: 19.521673
+Epoch [53], train_loss: 0.093551, val_loss: 0.093866, val_acc: 19.540894
+Epoch [54], train_loss: 0.093036, val_loss: 0.092864, val_acc: 19.823961
+Epoch [55], train_loss: 0.092525, val_loss: 0.091120, val_acc: 19.985107
+Epoch [56], train_loss: 0.092006, val_loss: 0.091247, val_acc: 20.038965
+Epoch [57], train_loss: 0.091506, val_loss: 0.090948, val_acc: 19.977587
+Epoch [58], train_loss: 0.091006, val_loss: 0.090268, val_acc: 20.235956
+Epoch [59], train_loss: 0.090529, val_loss: 0.089844, val_acc: 20.216711
+Epoch [60], train_loss: 0.090079, val_loss: 0.088457, val_acc: 20.555447
+Epoch [61], train_loss: 0.089598, val_loss: 0.087574, val_acc: 20.545286
+Epoch [62], train_loss: 0.089112, val_loss: 0.086896, val_acc: 20.649763
+Epoch [63], train_loss: 0.088741, val_loss: 0.087372, val_acc: 20.893387
+Epoch [64], train_loss: 0.088294, val_loss: 0.087765, val_acc: 20.684933
+Epoch [65], train_loss: 0.087786, val_loss: 0.086510, val_acc: 20.736408
+Epoch [66], train_loss: 0.087365, val_loss: 0.087301, val_acc: 20.636856
+Epoch [67], train_loss: 0.087005, val_loss: 0.086476, val_acc: 20.855677
+Epoch [68], train_loss: 0.086537, val_loss: 0.085397, val_acc: 21.082546
+Epoch [69], train_loss: 0.086144, val_loss: 0.083708, val_acc: 21.340586
+Epoch [70], train_loss: 0.085828, val_loss: 0.085874, val_acc: 21.105537
+Epoch [71], train_loss: 0.085345, val_loss: 0.082912, val_acc: 21.538092
+Epoch [72], train_loss: 0.084988, val_loss: 0.084117, val_acc: 21.315865
+Epoch [73], train_loss: 0.084631, val_loss: 0.083623, val_acc: 21.306980
+Epoch [74], train_loss: 0.084180, val_loss: 0.082817, val_acc: 21.508539
+Epoch [75], train_loss: 0.083861, val_loss: 0.083447, val_acc: 21.532007
+Epoch [76], train_loss: 0.083541, val_loss: 0.083304, val_acc: 21.612898
+Epoch [77], train_loss: 0.083155, val_loss: 0.082278, val_acc: 21.662210
+Epoch [78], train_loss: 0.082865, val_loss: 0.082178, val_acc: 21.623381
+Epoch [79], train_loss: 0.082529, val_loss: 0.080782, val_acc: 22.058908
+Epoch [80], train_loss: 0.082193, val_loss: 0.080895, val_acc: 21.848557
+Epoch [81], train_loss: 0.081775, val_loss: 0.080357, val_acc: 21.992245
+Epoch [82], train_loss: 0.081520, val_loss: 0.080381, val_acc: 22.064888
+Epoch [83], train_loss: 0.081178, val_loss: 0.080533, val_acc: 22.161787
+Epoch [84], train_loss: 0.080840, val_loss: 0.080094, val_acc: 22.058428
+Epoch [85], train_loss: 0.080560, val_loss: 0.079709, val_acc: 22.335075
+Epoch [86], train_loss: 0.080245, val_loss: 0.078706, val_acc: 22.397343
+Epoch [87], train_loss: 0.079905, val_loss: 0.079038, val_acc: 22.186777
+Epoch [88], train_loss: 0.079628, val_loss: 0.078419, val_acc: 22.483122
+Epoch [89], train_loss: 0.079349, val_loss: 0.079243, val_acc: 22.330900
+Epoch [90], train_loss: 0.079070, val_loss: 0.077394, val_acc: 22.491795
+Epoch [91], train_loss: 0.078758, val_loss: 0.077097, val_acc: 22.727879
+Epoch [92], train_loss: 0.078480, val_loss: 0.076954, val_acc: 22.731174
+Epoch [93], train_loss: 0.078227, val_loss: 0.077943, val_acc: 22.330051
+Epoch [94], train_loss: 0.077924, val_loss: 0.077844, val_acc: 22.466967
+Epoch [95], train_loss: 0.077662, val_loss: 0.076888, val_acc: 22.608391
+Epoch [96], train_loss: 0.077513, val_loss: 0.075444, val_acc: 22.785234
+Epoch [97], train_loss: 0.077237, val_loss: 0.077018, val_acc: 22.557318
+Epoch [98], train_loss: 0.076919, val_loss: 0.076711, val_acc: 22.700571
+Epoch [99], train_loss: 0.076650, val_loss: 0.075454, val_acc: 22.951033
+Epoch [100], train_loss: 0.076487, val_loss: 0.076320, val_acc: 22.873981
+Epoch [101], train_loss: 0.076238, val_loss: 0.075717, val_acc: 22.952358
+Epoch [102], train_loss: 0.075966, val_loss: 0.075315, val_acc: 23.100945
+Epoch [103], train_loss: 0.075729, val_loss: 0.075044, val_acc: 23.020905
+Epoch [104], train_loss: 0.075480, val_loss: 0.076508, val_acc: 22.933832
+Epoch [105], train_loss: 0.075386, val_loss: 0.073968, val_acc: 23.288246
+Epoch [106], train_loss: 0.075037, val_loss: 0.074631, val_acc: 23.070280
+Epoch [107], train_loss: 0.074872, val_loss: 0.073316, val_acc: 23.332312
+Epoch [108], train_loss: 0.074582, val_loss: 0.073267, val_acc: 23.437178
+Epoch [109], train_loss: 0.074486, val_loss: 0.074066, val_acc: 23.274363
+Epoch [110], train_loss: 0.074234, val_loss: 0.073202, val_acc: 23.433764
+Epoch [111], train_loss: 0.074082, val_loss: 0.072480, val_acc: 23.480070
+Epoch [112], train_loss: 0.073656, val_loss: 0.073543, val_acc: 23.354683
+Epoch [113], train_loss: 0.073539, val_loss: 0.072875, val_acc: 23.344801
+Epoch [114], train_loss: 0.073265, val_loss: 0.072819, val_acc: 23.461727
+Epoch [115], train_loss: 0.073134, val_loss: 0.072121, val_acc: 23.542179
+Epoch [116], train_loss: 0.072978, val_loss: 0.072515, val_acc: 23.488787
+Epoch [117], train_loss: 0.072673, val_loss: 0.072741, val_acc: 23.454857
+Epoch [118], train_loss: 0.072517, val_loss: 0.072281, val_acc: 23.510241
+Epoch [119], train_loss: 0.072260, val_loss: 0.071816, val_acc: 23.568266
+Epoch [120], train_loss: 0.072163, val_loss: 0.071990, val_acc: 23.564947
+Epoch [121], train_loss: 0.071949, val_loss: 0.071111, val_acc: 23.827917
+Epoch [122], train_loss: 0.071749, val_loss: 0.072101, val_acc: 23.608578
+Epoch [123], train_loss: 0.071593, val_loss: 0.071265, val_acc: 23.768745
+Epoch [124], train_loss: 0.071372, val_loss: 0.070242, val_acc: 23.819780
+Epoch [125], train_loss: 0.071221, val_loss: 0.070767, val_acc: 23.861578
+Epoch [126], train_loss: 0.071155, val_loss: 0.071015, val_acc: 23.754717
+Epoch [127], train_loss: 0.070993, val_loss: 0.070816, val_acc: 23.828474
+Epoch [128], train_loss: 0.070711, val_loss: 0.070334, val_acc: 23.897505
+Epoch [129], train_loss: 0.070498, val_loss: 0.069441, val_acc: 23.980667
+Epoch [130], train_loss: 0.070326, val_loss: 0.069309, val_acc: 24.009407
+Epoch [131], train_loss: 0.070278, val_loss: 0.068893, val_acc: 24.026001
+Epoch [132], train_loss: 0.070023, val_loss: 0.069820, val_acc: 23.971176
+Epoch [133], train_loss: 0.070052, val_loss: 0.068626, val_acc: 24.067001
+Epoch [134], train_loss: 0.069841, val_loss: 0.068665, val_acc: 24.070045
+Epoch [135], train_loss: 0.069555, val_loss: 0.068910, val_acc: 24.082697
+Epoch [136], train_loss: 0.069317, val_loss: 0.069451, val_acc: 24.019739
+Epoch [137], train_loss: 0.069304, val_loss: 0.068522, val_acc: 24.119503
+Epoch [138], train_loss: 0.069123, val_loss: 0.069442, val_acc: 24.046461
+Epoch [139], train_loss: 0.069000, val_loss: 0.068346, val_acc: 24.236029
+Epoch [140], train_loss: 0.068891, val_loss: 0.068227, val_acc: 24.205616
+Epoch [141], train_loss: 0.068758, val_loss: 0.069170, val_acc: 24.083561
+Epoch [142], train_loss: 0.068513, val_loss: 0.067540, val_acc: 24.291275
+Epoch [143], train_loss: 0.068378, val_loss: 0.066778, val_acc: 24.394650
+Epoch [144], train_loss: 0.068345, val_loss: 0.068085, val_acc: 24.222805
+Epoch [145], train_loss: 0.068125, val_loss: 0.067106, val_acc: 24.327419
+Epoch [146], train_loss: 0.068096, val_loss: 0.067304, val_acc: 24.364294
+Epoch [147], train_loss: 0.067871, val_loss: 0.067419, val_acc: 24.366154
+Epoch [148], train_loss: 0.067756, val_loss: 0.067109, val_acc: 24.355080
+Epoch [149], train_loss: 0.067511, val_loss: 0.067230, val_acc: 24.312937
+Epoch [150], train_loss: 0.067433, val_loss: 0.066101, val_acc: 24.457005
+Epoch [151], train_loss: 0.067398, val_loss: 0.066920, val_acc: 24.341141
+Epoch [152], train_loss: 0.067363, val_loss: 0.067397, val_acc: 24.315857
+Epoch [153], train_loss: 0.066996, val_loss: 0.066457, val_acc: 24.425598
+Epoch [154], train_loss: 0.066910, val_loss: 0.066253, val_acc: 24.462431
+Epoch [155], train_loss: 0.066821, val_loss: 0.067139, val_acc: 24.375160
+Epoch [156], train_loss: 0.066811, val_loss: 0.066303, val_acc: 24.437571
+Epoch [157], train_loss: 0.066552, val_loss: 0.066707, val_acc: 24.482498
+Epoch [158], train_loss: 0.066475, val_loss: 0.065446, val_acc: 24.586679
+Epoch [159], train_loss: 0.066375, val_loss: 0.066060, val_acc: 24.522400
+Epoch [160], train_loss: 0.066260, val_loss: 0.065814, val_acc: 24.517448
+Epoch [161], train_loss: 0.066064, val_loss: 0.065371, val_acc: 24.604624
+Epoch [162], train_loss: 0.066022, val_loss: 0.066011, val_acc: 24.459154
+Epoch [163], train_loss: 0.065918, val_loss: 0.065268, val_acc: 24.586090
+Epoch [164], train_loss: 0.065774, val_loss: 0.065574, val_acc: 24.622461
+Epoch [165], train_loss: 0.065850, val_loss: 0.065903, val_acc: 24.567410
+Epoch [166], train_loss: 0.065631, val_loss: 0.065277, val_acc: 24.586939
+Epoch [167], train_loss: 0.065394, val_loss: 0.065555, val_acc: 24.636776
+Epoch [168], train_loss: 0.065313, val_loss: 0.064803, val_acc: 24.688942
+Epoch [169], train_loss: 0.065194, val_loss: 0.065159, val_acc: 24.656382
+Epoch [170], train_loss: 0.065054, val_loss: 0.064291, val_acc: 24.728289
+Epoch [171], train_loss: 0.065219, val_loss: 0.064543, val_acc: 24.709522
+Epoch [172], train_loss: 0.065122, val_loss: 0.065098, val_acc: 24.670252
+Epoch [173], train_loss: 0.064869, val_loss: 0.064725, val_acc: 24.727219
+Epoch [174], train_loss: 0.064744, val_loss: 0.064419, val_acc: 24.766701
+Epoch [175], train_loss: 0.064524, val_loss: 0.064378, val_acc: 24.789951
+Epoch [176], train_loss: 0.064575, val_loss: 0.064049, val_acc: 24.774330
+Epoch [177], train_loss: 0.064448, val_loss: 0.064096, val_acc: 24.775156
+Epoch [178], train_loss: 0.064302, val_loss: 0.064262, val_acc: 24.741926
+Epoch [179], train_loss: 0.064163, val_loss: 0.063883, val_acc: 24.835398
+Epoch [180], train_loss: 0.064133, val_loss: 0.064083, val_acc: 24.802834
+Epoch [181], train_loss: 0.063942, val_loss: 0.063777, val_acc: 24.837151
+Epoch [182], train_loss: 0.064035, val_loss: 0.063998, val_acc: 24.778284
+Epoch [183], train_loss: 0.063924, val_loss: 0.063486, val_acc: 24.825924
+Epoch [184], train_loss: 0.063833, val_loss: 0.063776, val_acc: 24.825951
+Epoch [185], train_loss: 0.063786, val_loss: 0.063685, val_acc: 24.844299
+Epoch [186], train_loss: 0.063605, val_loss: 0.063938, val_acc: 24.803738
+Epoch [187], train_loss: 0.063484, val_loss: 0.063079, val_acc: 24.891907
+Epoch [188], train_loss: 0.063461, val_loss: 0.062919, val_acc: 24.931053
+Epoch [189], train_loss: 0.063397, val_loss: 0.063053, val_acc: 24.944374
+Epoch [190], train_loss: 0.063223, val_loss: 0.063219, val_acc: 24.912642
+Epoch [191], train_loss: 0.063157, val_loss: 0.062983, val_acc: 24.930067
+Epoch [192], train_loss: 0.063123, val_loss: 0.063053, val_acc: 24.947168
+Epoch [193], train_loss: 0.062972, val_loss: 0.062899, val_acc: 24.950567
+Epoch [194], train_loss: 0.062806, val_loss: 0.062763, val_acc: 24.970823
+Epoch [195], train_loss: 0.062764, val_loss: 0.062925, val_acc: 24.963312
+Epoch [196], train_loss: 0.062762, val_loss: 0.062722, val_acc: 24.985998
+Epoch [197], train_loss: 0.062603, val_loss: 0.062547, val_acc: 24.987179
+Epoch [198], train_loss: 0.062569, val_loss: 0.062667, val_acc: 24.969275
+Epoch [199], train_loss: 0.062458, val_loss: 0.062318, val_acc: 25.002949
+Epoch [200], train_loss: 0.062379, val_loss: 0.061932, val_acc: 25.043846
+Epoch [201], train_loss: 0.062369, val_loss: 0.062746, val_acc: 24.931763
+Epoch [202], train_loss: 0.062186, val_loss: 0.062027, val_acc: 25.019938
+Epoch [203], train_loss: 0.062144, val_loss: 0.062561, val_acc: 24.982771
+Epoch [204], train_loss: 0.062167, val_loss: 0.062341, val_acc: 24.988132
+Epoch [205], train_loss: 0.062076, val_loss: 0.062071, val_acc: 25.074732
+Epoch [206], train_loss: 0.061888, val_loss: 0.061922, val_acc: 25.039026
+Epoch [207], train_loss: 0.061816, val_loss: 0.061980, val_acc: 25.027479
+Epoch [208], train_loss: 0.061701, val_loss: 0.061925, val_acc: 24.949318
+Epoch [209], train_loss: 0.061678, val_loss: 0.062025, val_acc: 25.058867
+Epoch [210], train_loss: 0.061507, val_loss: 0.061687, val_acc: 25.088144
+Epoch [211], train_loss: 0.061527, val_loss: 0.061955, val_acc: 25.107868
+Epoch [212], train_loss: 0.061440, val_loss: 0.061612, val_acc: 25.090820
+Epoch [213], train_loss: 0.061483, val_loss: 0.061493, val_acc: 25.092159
+Epoch [214], train_loss: 0.061190, val_loss: 0.061304, val_acc: 25.141762
+Epoch [215], train_loss: 0.061162, val_loss: 0.061640, val_acc: 25.047058
+Epoch [216], train_loss: 0.061111, val_loss: 0.061024, val_acc: 25.082443
+Epoch [217], train_loss: 0.061044, val_loss: 0.061163, val_acc: 25.191208
+Epoch [218], train_loss: 0.060971, val_loss: 0.061077, val_acc: 25.171705
+Epoch [219], train_loss: 0.060946, val_loss: 0.061008, val_acc: 25.205488
+Epoch [220], train_loss: 0.060823, val_loss: 0.061358, val_acc: 25.172905
+Epoch [221], train_loss: 0.060782, val_loss: 0.060887, val_acc: 25.170599
+Epoch [222], train_loss: 0.060737, val_loss: 0.060807, val_acc: 25.208042
+Epoch [223], train_loss: 0.060642, val_loss: 0.060761, val_acc: 25.190571
+Epoch [224], train_loss: 0.060581, val_loss: 0.060451, val_acc: 25.227257
+Epoch [225], train_loss: 0.060546, val_loss: 0.060695, val_acc: 25.211662
+Epoch [226], train_loss: 0.060368, val_loss: 0.060515, val_acc: 25.190964
+Epoch [227], train_loss: 0.060405, val_loss: 0.060780, val_acc: 25.168589
+Epoch [228], train_loss: 0.060226, val_loss: 0.060551, val_acc: 25.247156
+Epoch [229], train_loss: 0.060220, val_loss: 0.060417, val_acc: 25.278584
+Epoch [230], train_loss: 0.060203, val_loss: 0.060869, val_acc: 25.207596
+Epoch [231], train_loss: 0.060078, val_loss: 0.060110, val_acc: 25.264265
+Epoch [232], train_loss: 0.060015, val_loss: 0.060303, val_acc: 25.217438
+Epoch [233], train_loss: 0.059942, val_loss: 0.060418, val_acc: 25.179745
+Epoch [234], train_loss: 0.059865, val_loss: 0.060187, val_acc: 25.181944
+Epoch [235], train_loss: 0.059904, val_loss: 0.060403, val_acc: 25.264593
+Epoch [236], train_loss: 0.059870, val_loss: 0.060530, val_acc: 25.188084
+Epoch [237], train_loss: 0.059723, val_loss: 0.060064, val_acc: 25.264656
+Epoch [238], train_loss: 0.059604, val_loss: 0.060405, val_acc: 25.173161
+Epoch [239], train_loss: 0.059523, val_loss: 0.059888, val_acc: 25.247705
+Epoch [240], train_loss: 0.059526, val_loss: 0.059829, val_acc: 25.276270
+Epoch [241], train_loss: 0.059496, val_loss: 0.059633, val_acc: 25.241547
+Epoch [242], train_loss: 0.059402, val_loss: 0.059694, val_acc: 25.283955
+Epoch [243], train_loss: 0.059357, val_loss: 0.059975, val_acc: 25.237831
+Epoch [244], train_loss: 0.059269, val_loss: 0.059636, val_acc: 25.343990
+Epoch [245], train_loss: 0.059201, val_loss: 0.059753, val_acc: 25.215870
+Epoch [246], train_loss: 0.059138, val_loss: 0.059672, val_acc: 25.389509
+Epoch [247], train_loss: 0.059102, val_loss: 0.059584, val_acc: 25.328165
+Epoch [248], train_loss: 0.059103, val_loss: 0.059723, val_acc: 25.311815
+Epoch [249], train_loss: 0.059024, val_loss: 0.059359, val_acc: 25.285322
+Epoch [250], train_loss: 0.058910, val_loss: 0.059420, val_acc: 25.324839
+Epoch [251], train_loss: 0.058915, val_loss: 0.059555, val_acc: 25.293291
+Epoch [252], train_loss: 0.058903, val_loss: 0.059294, val_acc: 25.371620
+Epoch [253], train_loss: 0.058859, val_loss: 0.059449, val_acc: 25.326412
+Epoch [254], train_loss: 0.058775, val_loss: 0.059389, val_acc: 25.356159
+Epoch [255], train_loss: 0.058706, val_loss: 0.059550, val_acc: 25.339622
+Epoch [256], train_loss: 0.058699, val_loss: 0.059456, val_acc: 25.332512
+Epoch [257], train_loss: 0.058645, val_loss: 0.059167, val_acc: 25.345634
+Epoch [258], train_loss: 0.058555, val_loss: 0.059416, val_acc: 25.260870
+Epoch [259], train_loss: 0.058556, val_loss: 0.059348, val_acc: 25.340582
+Epoch [260], train_loss: 0.058494, val_loss: 0.059132, val_acc: 25.320633
+Epoch [261], train_loss: 0.058405, val_loss: 0.059012, val_acc: 25.378252
+Epoch [262], train_loss: 0.058427, val_loss: 0.058977, val_acc: 25.298149
+Epoch [263], train_loss: 0.058335, val_loss: 0.059162, val_acc: 25.339912
+Epoch [264], train_loss: 0.058310, val_loss: 0.059064, val_acc: 25.285650
+Epoch [265], train_loss: 0.058268, val_loss: 0.059063, val_acc: 25.316668
+Epoch [266], train_loss: 0.058241, val_loss: 0.059075, val_acc: 25.349161
+Epoch [267], train_loss: 0.058169, val_loss: 0.059280, val_acc: 25.332071
+Epoch [268], train_loss: 0.058163, val_loss: 0.059018, val_acc: 25.335537
+Epoch [269], train_loss: 0.058061, val_loss: 0.059021, val_acc: 25.288694
+Epoch [270], train_loss: 0.058034, val_loss: 0.058981, val_acc: 25.389727
+Epoch [271], train_loss: 0.058015, val_loss: 0.058703, val_acc: 25.324085
+Epoch [272], train_loss: 0.058026, val_loss: 0.058966, val_acc: 25.339384
+Epoch [273], train_loss: 0.057953, val_loss: 0.058804, val_acc: 25.360264
+Epoch [274], train_loss: 0.057932, val_loss: 0.058716, val_acc: 25.356644
+Epoch [275], train_loss: 0.057893, val_loss: 0.058737, val_acc: 25.379137
+Epoch [276], train_loss: 0.057905, val_loss: 0.059064, val_acc: 25.350855
+Epoch [277], train_loss: 0.057781, val_loss: 0.058845, val_acc: 25.278835
+Epoch [278], train_loss: 0.057770, val_loss: 0.058780, val_acc: 25.341579
+Epoch [279], train_loss: 0.057700, val_loss: 0.058789, val_acc: 25.264605
+Epoch [280], train_loss: 0.057711, val_loss: 0.058827, val_acc: 25.332586
+Epoch [281], train_loss: 0.057679, val_loss: 0.058614, val_acc: 25.252195
+Epoch [282], train_loss: 0.057615, val_loss: 0.058814, val_acc: 25.315605
+Epoch [283], train_loss: 0.057652, val_loss: 0.058658, val_acc: 25.241699
+Epoch [284], train_loss: 0.057547, val_loss: 0.059034, val_acc: 25.274260
+Epoch [285], train_loss: 0.057565, val_loss: 0.058615, val_acc: 25.291504
+Epoch [286], train_loss: 0.057562, val_loss: 0.058729, val_acc: 25.332563
+Epoch [287], train_loss: 0.057542, val_loss: 0.058795, val_acc: 25.345884
+Epoch [288], train_loss: 0.057413, val_loss: 0.058676, val_acc: 25.345268
+Epoch [289], train_loss: 0.057453, val_loss: 0.058786, val_acc: 25.251856
+Epoch [290], train_loss: 0.057418, val_loss: 0.058648, val_acc: 25.316210
+Epoch [291], train_loss: 0.057460, val_loss: 0.058691, val_acc: 25.280067
+Epoch [292], train_loss: 0.057405, val_loss: 0.058559, val_acc: 25.233353
+Epoch [293], train_loss: 0.057301, val_loss: 0.058610, val_acc: 25.195616
+Epoch [294], train_loss: 0.057277, val_loss: 0.058550, val_acc: 25.273893
+Epoch [295], train_loss: 0.057263, val_loss: 0.058627, val_acc: 25.320139
+Epoch [296], train_loss: 0.057271, val_loss: 0.058846, val_acc: 25.337646
+Epoch [297], train_loss: 0.057238, val_loss: 0.058523, val_acc: 25.250841
+Epoch [298], train_loss: 0.057175, val_loss: 0.058702, val_acc: 25.206165
+Epoch [299], train_loss: 0.057164, val_loss: 0.058610, val_acc: 25.361307
+Epoch [300], train_loss: 0.057140, val_loss: 0.058584, val_acc: 25.272650
+Epoch [301], train_loss: 0.057120, val_loss: 0.058675, val_acc: 25.167049
+Epoch [302], train_loss: 0.057062, val_loss: 0.058473, val_acc: 25.252975
+Epoch [303], train_loss: 0.057085, val_loss: 0.058726, val_acc: 25.201260
+Epoch [304], train_loss: 0.057020, val_loss: 0.058635, val_acc: 25.243006
+Epoch [305], train_loss: 0.057094, val_loss: 0.058858, val_acc: 25.271076
+Epoch [306], train_loss: 0.057156, val_loss: 0.058500, val_acc: 25.212643
+Epoch [307], train_loss: 0.057023, val_loss: 0.058603, val_acc: 25.260481
+Epoch [308], train_loss: 0.056969, val_loss: 0.058487, val_acc: 25.158882
+Epoch [309], train_loss: 0.056966, val_loss: 0.058438, val_acc: 25.180557
+Epoch [310], train_loss: 0.056942, val_loss: 0.058552, val_acc: 25.201801
+Epoch [311], train_loss: 0.056954, val_loss: 0.058453, val_acc: 25.225498
+Epoch [312], train_loss: 0.056925, val_loss: 0.058627, val_acc: 25.138891
+Epoch [313], train_loss: 0.056875, val_loss: 0.058604, val_acc: 25.263832
+Epoch [314], train_loss: 0.056858, val_loss: 0.058531, val_acc: 25.183922
+Epoch [315], train_loss: 0.056862, val_loss: 0.058597, val_acc: 25.147087
+Epoch [316], train_loss: 0.056844, val_loss: 0.058455, val_acc: 25.207661
+Epoch [317], train_loss: 0.056805, val_loss: 0.058497, val_acc: 25.195061
+Epoch [318], train_loss: 0.056778, val_loss: 0.058455, val_acc: 25.165594
+Epoch [319], train_loss: 0.056746, val_loss: 0.058663, val_acc: 25.230539
+Epoch [320], train_loss: 0.056732, val_loss: 0.058551, val_acc: 25.186356
+Epoch [321], train_loss: 0.056759, val_loss: 0.058509, val_acc: 25.123123
+Epoch [322], train_loss: 0.056703, val_loss: 0.058762, val_acc: 25.158739
+Epoch [323], train_loss: 0.056713, val_loss: 0.058598, val_acc: 25.035017
+Epoch [324], train_loss: 0.056662, val_loss: 0.058553, val_acc: 25.061670
+Epoch [325], train_loss: 0.056700, val_loss: 0.058540, val_acc: 25.187416
+Epoch [326], train_loss: 0.056652, val_loss: 0.058476, val_acc: 25.160154
+Epoch [327], train_loss: 0.056595, val_loss: 0.058498, val_acc: 25.079163
+Epoch [328], train_loss: 0.056686, val_loss: 0.058592, val_acc: 25.115047
+Epoch [329], train_loss: 0.056617, val_loss: 0.058586, val_acc: 25.104944
+Epoch [330], train_loss: 0.056593, val_loss: 0.058457, val_acc: 25.036335
+Epoch [331], train_loss: 0.056584, val_loss: 0.058824, val_acc: 25.135752
+Epoch [332], train_loss: 0.056588, val_loss: 0.058531, val_acc: 25.045567
+Epoch [333], train_loss: 0.056541, val_loss: 0.058559, val_acc: 25.064650
+Epoch [334], train_loss: 0.056928, val_loss: 0.058860, val_acc: 25.096718
+Epoch [335], train_loss: 0.056662, val_loss: 0.058485, val_acc: 25.032448
+Epoch [336], train_loss: 0.056585, val_loss: 0.058641, val_acc: 25.010241
+Epoch [337], train_loss: 0.056551, val_loss: 0.058605, val_acc: 24.899849
+Epoch [338], train_loss: 0.056561, val_loss: 0.058583, val_acc: 25.042702
+Epoch [339], train_loss: 0.056531, val_loss: 0.058648, val_acc: 25.028442
+Epoch [340], train_loss: 0.056472, val_loss: 0.058747, val_acc: 25.037449
+Epoch [341], train_loss: 0.056473, val_loss: 0.058651, val_acc: 25.077415
+Epoch [342], train_loss: 0.056487, val_loss: 0.058592, val_acc: 24.961334
+Epoch [343], train_loss: 0.056489, val_loss: 0.058758, val_acc: 25.059858
+Epoch [344], train_loss: 0.056445, val_loss: 0.058503, val_acc: 25.057846
+Epoch [345], train_loss: 0.056440, val_loss: 0.058543, val_acc: 24.996565
+Epoch [346], train_loss: 0.056407, val_loss: 0.058590, val_acc: 25.027615
+Epoch [347], train_loss: 0.056395, val_loss: 0.058822, val_acc: 25.059202
+Epoch [348], train_loss: 0.056427, val_loss: 0.058614, val_acc: 25.097832
+Epoch [349], train_loss: 0.056383, val_loss: 0.058548, val_acc: 24.976967
+Epoch [350], train_loss: 0.056352, val_loss: 0.058738, val_acc: 25.020800
+Epoch [351], train_loss: 0.056329, val_loss: 0.058649, val_acc: 24.977539
+Epoch [352], train_loss: 0.056336, val_loss: 0.058767, val_acc: 24.861557
+Epoch [353], train_loss: 0.056302, val_loss: 0.058614, val_acc: 25.055956
+Epoch [354], train_loss: 0.056327, val_loss: 0.058568, val_acc: 24.915781
+Epoch [355], train_loss: 0.056326, val_loss: 0.058650, val_acc: 24.994062
+Epoch [356], train_loss: 0.056313, val_loss: 0.058587, val_acc: 25.075649
+Epoch [357], train_loss: 0.056262, val_loss: 0.058578, val_acc: 25.023003
+Epoch [358], train_loss: 0.056294, val_loss: 0.058647, val_acc: 24.899134
+Epoch [359], train_loss: 0.056210, val_loss: 0.058632, val_acc: 24.857243
+Epoch [360], train_loss: 0.056263, val_loss: 0.058681, val_acc: 24.974615
+Epoch [361], train_loss: 0.056253, val_loss: 0.058727, val_acc: 24.932444
+Epoch [362], train_loss: 0.056688, val_loss: 0.058705, val_acc: 24.951267
+Epoch [363], train_loss: 0.056257, val_loss: 0.058544, val_acc: 24.976753
+Epoch [364], train_loss: 0.056243, val_loss: 0.058541, val_acc: 24.952324
+Epoch [365], train_loss: 0.056247, val_loss: 0.058641, val_acc: 24.932312
+Epoch [366], train_loss: 0.056257, val_loss: 0.058645, val_acc: 24.963440
+Epoch [367], train_loss: 0.056246, val_loss: 0.058873, val_acc: 24.786253
+Epoch [368], train_loss: 0.056186, val_loss: 0.058677, val_acc: 24.902145
+Epoch [369], train_loss: 0.056188, val_loss: 0.058637, val_acc: 25.016525
+Epoch [370], train_loss: 0.056162, val_loss: 0.058656, val_acc: 24.921614
+Epoch [371], train_loss: 0.056167, val_loss: 0.058645, val_acc: 24.952715
+Epoch [372], train_loss: 0.056145, val_loss: 0.058588, val_acc: 24.857895
+Epoch [373], train_loss: 0.056134, val_loss: 0.058619, val_acc: 24.954460
+Epoch [374], train_loss: 0.056147, val_loss: 0.058605, val_acc: 24.878489
+Epoch [375], train_loss: 0.056143, val_loss: 0.058712, val_acc: 24.916124
+Epoch [376], train_loss: 0.056116, val_loss: 0.058803, val_acc: 24.942572
+Epoch [377], train_loss: 0.056098, val_loss: 0.058733, val_acc: 24.855150
+Epoch [378], train_loss: 0.056155, val_loss: 0.058732, val_acc: 24.930374
+Epoch [379], train_loss: 0.056100, val_loss: 0.058640, val_acc: 24.918627
+Epoch [380], train_loss: 0.056089, val_loss: 0.058620, val_acc: 24.959864
+Epoch [381], train_loss: 0.056061, val_loss: 0.058746, val_acc: 24.902958
+Epoch [382], train_loss: 0.056049, val_loss: 0.058727, val_acc: 24.840563
+Epoch [383], train_loss: 0.056066, val_loss: 0.058760, val_acc: 24.941130
+Epoch [384], train_loss: 0.056028, val_loss: 0.058682, val_acc: 24.883636
+Epoch [385], train_loss: 0.056041, val_loss: 0.058641, val_acc: 24.817522
+Epoch [386], train_loss: 0.056004, val_loss: 0.058770, val_acc: 24.842091
+Epoch [387], train_loss: 0.056016, val_loss: 0.058609, val_acc: 24.875822
+Epoch [388], train_loss: 0.055979, val_loss: 0.058710, val_acc: 24.836393
+Epoch [389], train_loss: 0.055996, val_loss: 0.058817, val_acc: 24.765011
+Epoch [390], train_loss: 0.055979, val_loss: 0.058846, val_acc: 24.753801
+Epoch [391], train_loss: 0.055988, val_loss: 0.058757, val_acc: 24.820177
+Epoch [392], train_loss: 0.056004, val_loss: 0.058702, val_acc: 24.918535
+Epoch [393], train_loss: 0.055972, val_loss: 0.058777, val_acc: 24.795124
+Epoch [394], train_loss: 0.055987, val_loss: 0.058722, val_acc: 24.818466
+Epoch [395], train_loss: 0.056057, val_loss: 0.058757, val_acc: 24.862690
+Epoch [396], train_loss: 0.055947, val_loss: 0.058622, val_acc: 24.890987
+Epoch [397], train_loss: 0.055913, val_loss: 0.058784, val_acc: 24.694557
+Epoch [398], train_loss: 0.055922, val_loss: 0.058646, val_acc: 24.775326
+Epoch [399], train_loss: 0.055907, val_loss: 0.058778, val_acc: 24.809048
+Epoch [400], train_loss: 0.055903, val_loss: 0.058975, val_acc: 24.707869
+Epoch [401], train_loss: 0.055872, val_loss: 0.058688, val_acc: 24.845789
+Epoch [402], train_loss: 0.055916, val_loss: 0.058801, val_acc: 24.766157
+Epoch [403], train_loss: 0.055894, val_loss: 0.058712, val_acc: 24.831915
+Epoch [404], train_loss: 0.055847, val_loss: 0.058838, val_acc: 24.805201
+Epoch [405], train_loss: 0.055825, val_loss: 0.058909, val_acc: 24.750425
+Epoch [406], train_loss: 0.055859, val_loss: 0.058911, val_acc: 24.735413
+Epoch [407], train_loss: 0.055850, val_loss: 0.058736, val_acc: 24.812099
+Epoch [408], train_loss: 0.055816, val_loss: 0.058819, val_acc: 24.836216
+Epoch [409], train_loss: 0.056213, val_loss: 0.058849, val_acc: 24.956753
+Epoch [410], train_loss: 0.055822, val_loss: 0.058756, val_acc: 24.752966
+Epoch [411], train_loss: 0.055796, val_loss: 0.058832, val_acc: 24.730682
+Epoch [412], train_loss: 0.055799, val_loss: 0.058705, val_acc: 24.815384
+Epoch [413], train_loss: 0.055786, val_loss: 0.058814, val_acc: 24.740780
+Epoch [414], train_loss: 0.055753, val_loss: 0.058717, val_acc: 24.753609
+Epoch [415], train_loss: 0.055737, val_loss: 0.059012, val_acc: 24.607021
+Epoch [416], train_loss: 0.055786, val_loss: 0.058776, val_acc: 24.681719
+Epoch [417], train_loss: 0.055732, val_loss: 0.058755, val_acc: 24.703754
+Epoch [418], train_loss: 0.055723, val_loss: 0.058675, val_acc: 24.649433
+Epoch [419], train_loss: 0.055711, val_loss: 0.058750, val_acc: 24.742306
+Epoch [420], train_loss: 0.055704, val_loss: 0.058837, val_acc: 24.782927
+Epoch [421], train_loss: 0.055680, val_loss: 0.058876, val_acc: 24.723215
+Epoch [422], train_loss: 0.055701, val_loss: 0.058955, val_acc: 24.777105
+Epoch [423], train_loss: 0.055666, val_loss: 0.058868, val_acc: 24.645372
+Epoch [424], train_loss: 0.055666, val_loss: 0.058972, val_acc: 24.593357
+Epoch [425], train_loss: 0.055659, val_loss: 0.058931, val_acc: 24.716906
+Epoch [426], train_loss: 0.055663, val_loss: 0.058798, val_acc: 24.716122
+Epoch [427], train_loss: 0.055648, val_loss: 0.058872, val_acc: 24.729237
+Epoch [428], train_loss: 0.055631, val_loss: 0.058816, val_acc: 24.655537
+Epoch [429], train_loss: 0.055666, val_loss: 0.059114, val_acc: 24.666580
+Epoch [430], train_loss: 0.055610, val_loss: 0.058839, val_acc: 24.752327
+Epoch [431], train_loss: 0.055598, val_loss: 0.058958, val_acc: 24.679386
+Epoch [432], train_loss: 0.055575, val_loss: 0.058960, val_acc: 24.671518
+Epoch [433], train_loss: 0.055563, val_loss: 0.059042, val_acc: 24.628555
+Epoch [434], train_loss: 0.055563, val_loss: 0.058880, val_acc: 24.692696
+Epoch [435], train_loss: 0.055560, val_loss: 0.058920, val_acc: 24.673109
+Epoch [436], train_loss: 0.055582, val_loss: 0.059003, val_acc: 24.774305
+Epoch [437], train_loss: 0.055556, val_loss: 0.058865, val_acc: 24.564806
+Epoch [438], train_loss: 0.055516, val_loss: 0.058970, val_acc: 24.618536
+Epoch [439], train_loss: 0.055538, val_loss: 0.058878, val_acc: 24.696314
+Epoch [440], train_loss: 0.055550, val_loss: 0.058864, val_acc: 24.649199
+Epoch [441], train_loss: 0.055523, val_loss: 0.058904, val_acc: 24.683220
+Epoch [442], train_loss: 0.055551, val_loss: 0.058908, val_acc: 24.608831
+Epoch [443], train_loss: 0.055468, val_loss: 0.058919, val_acc: 24.454029
+Epoch [444], train_loss: 0.055461, val_loss: 0.058974, val_acc: 24.463755
+Epoch [445], train_loss: 0.055486, val_loss: 0.058874, val_acc: 24.619602
+Epoch [446], train_loss: 0.055478, val_loss: 0.059032, val_acc: 24.543623
+Epoch [447], train_loss: 0.055437, val_loss: 0.058830, val_acc: 24.561934
+Epoch [448], train_loss: 0.055442, val_loss: 0.059035, val_acc: 24.382658
+Epoch [449], train_loss: 0.055459, val_loss: 0.058892, val_acc: 24.657734
+Epoch [450], train_loss: 0.055416, val_loss: 0.059087, val_acc: 24.619944
+Epoch [451], train_loss: 0.055383, val_loss: 0.058923, val_acc: 24.703964
+Epoch [452], train_loss: 0.055418, val_loss: 0.058929, val_acc: 24.427204
+Epoch [453], train_loss: 0.055404, val_loss: 0.058936, val_acc: 24.491282
+Epoch [454], train_loss: 0.055380, val_loss: 0.058979, val_acc: 24.491156
+Epoch [455], train_loss: 0.055369, val_loss: 0.059110, val_acc: 24.497931
+Epoch [456], train_loss: 0.055408, val_loss: 0.058971, val_acc: 24.631693
+Epoch [457], train_loss: 0.055358, val_loss: 0.059150, val_acc: 24.564938
+Epoch [458], train_loss: 0.055365, val_loss: 0.059128, val_acc: 24.558764
+Epoch [459], train_loss: 0.055324, val_loss: 0.059068, val_acc: 24.565735
+Epoch [460], train_loss: 0.055302, val_loss: 0.059069, val_acc: 24.441252
+Epoch [461], train_loss: 0.055298, val_loss: 0.059282, val_acc: 24.608274
+Epoch [462], train_loss: 0.055314, val_loss: 0.059175, val_acc: 24.606941
+Epoch [463], train_loss: 0.055328, val_loss: 0.059102, val_acc: 24.621525
+Epoch [464], train_loss: 0.055302, val_loss: 0.059085, val_acc: 24.353428
+Epoch [465], train_loss: 0.055274, val_loss: 0.058963, val_acc: 24.493240
+Epoch [466], train_loss: 0.055234, val_loss: 0.059115, val_acc: 24.422155
+Epoch [467], train_loss: 0.055248, val_loss: 0.059289, val_acc: 24.486677
+Epoch [468], train_loss: 0.055222, val_loss: 0.059026, val_acc: 24.355164
+Epoch [469], train_loss: 0.055210, val_loss: 0.059144, val_acc: 24.431355
+Epoch [470], train_loss: 0.055224, val_loss: 0.059070, val_acc: 24.467546
+Epoch [471], train_loss: 0.055189, val_loss: 0.059147, val_acc: 24.392330
+Epoch [472], train_loss: 0.055203, val_loss: 0.059135, val_acc: 24.380531
+Epoch [473], train_loss: 0.055167, val_loss: 0.059037, val_acc: 24.343376
+Epoch [474], train_loss: 0.055168, val_loss: 0.059196, val_acc: 24.451990
+Epoch [475], train_loss: 0.055146, val_loss: 0.059047, val_acc: 24.527687
+Epoch [476], train_loss: 0.055151, val_loss: 0.059118, val_acc: 24.520525
+Epoch [477], train_loss: 0.055143, val_loss: 0.059065, val_acc: 24.433105
+Epoch [478], train_loss: 0.055114, val_loss: 0.059077, val_acc: 24.452665
+Epoch [479], train_loss: 0.055138, val_loss: 0.059191, val_acc: 24.443600
+Epoch [480], train_loss: 0.055151, val_loss: 0.059101, val_acc: 24.365648
+Epoch [481], train_loss: 0.055135, val_loss: 0.059408, val_acc: 24.240086
+Epoch [482], train_loss: 0.055123, val_loss: 0.059101, val_acc: 24.486496
+Epoch [483], train_loss: 0.055139, val_loss: 0.059247, val_acc: 24.306450
+Epoch [484], train_loss: 0.055074, val_loss: 0.059075, val_acc: 24.413904
+Epoch [485], train_loss: 0.055072, val_loss: 0.059144, val_acc: 24.466990
+Epoch [486], train_loss: 0.055096, val_loss: 0.059260, val_acc: 24.359474
+Epoch [487], train_loss: 0.055047, val_loss: 0.059150, val_acc: 24.278683
+Epoch [488], train_loss: 0.055040, val_loss: 0.059237, val_acc: 24.402044
+Epoch [489], train_loss: 0.055024, val_loss: 0.059120, val_acc: 24.351084
+Epoch [490], train_loss: 0.054990, val_loss: 0.059325, val_acc: 24.305077
+Epoch [491], train_loss: 0.055022, val_loss: 0.059141, val_acc: 24.394997
+Epoch [492], train_loss: 0.054996, val_loss: 0.059247, val_acc: 24.272638
+Epoch [493], train_loss: 0.055014, val_loss: 0.059328, val_acc: 24.455441
+Epoch [494], train_loss: 0.054937, val_loss: 0.059274, val_acc: 24.172031
+Epoch [495], train_loss: 0.054957, val_loss: 0.059262, val_acc: 24.395878
+Epoch [496], train_loss: 0.054994, val_loss: 0.059253, val_acc: 24.400946
+Epoch [497], train_loss: 0.054946, val_loss: 0.059235, val_acc: 24.342319
+Epoch [498], train_loss: 0.054922, val_loss: 0.059215, val_acc: 24.405720
+Epoch [499], train_loss: 0.054958, val_loss: 0.059264, val_acc: 24.375261
+python3 ./UNet_V10.py  4191.61s user 4063.69s system 99% cpu 2:17:38.83 total
diff --git a/UNet/Sim_logs/UNet_V11_25585645.log b/UNet/Sim_logs/UNet_V11_25585645.log
new file mode 100644
index 0000000000000000000000000000000000000000..262e5680337254358fb0b8e4e2d60107e5b99165
--- /dev/null
+++ b/UNet/Sim_logs/UNet_V11_25585645.log
@@ -0,0 +1,520 @@
+(OK) Loading cuda 10.2.89
+(OK) Loading python 3.7.11
+(!!) The SciPy Stack is available: http://www.scipy.org/stackspec.html
+ Built with GCC compilers.
+Collecting torch==1.10.1
+  Using cached torch-1.10.1-cp37-cp37m-manylinux1_x86_64.whl (881.9 MB)
+Collecting typing-extensions
+  Using cached typing_extensions-4.1.1-py3-none-any.whl (26 kB)
+Installing collected packages: typing-extensions, torch
+  WARNING: The scripts convert-caffe2-to-onnx, convert-onnx-to-caffe2 and torchrun are installed in '/home/yk138599/.local/bin' which is not on PATH.
+  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
+Successfully installed torch-1.10.1 typing-extensions-4.1.1
+WARNING: You are using pip version 21.2.4; however, version 22.0.3 is available.
+You should consider upgrading via the '/usr/local_rwth/sw/python/3.7.11/x86_64/bin/python3.7 -m pip install --upgrade pip' command.
+number auf epochs: 500
+batchsize: 32
+learning rate: 1e-05
+kernel size is: 5
+ seed is: 373686838
+Epoch [0], train_loss: 0.201484, val_loss: 0.166318, val_acc: 6.042302
+Epoch [1], train_loss: 0.194912, val_loss: 0.189360, val_acc: 6.667909
+Epoch [2], train_loss: 0.189009, val_loss: 0.188154, val_acc: 6.890604
+Epoch [3], train_loss: 0.183536, val_loss: 0.181660, val_acc: 7.258780
+Epoch [4], train_loss: 0.178365, val_loss: 0.177862, val_acc: 7.561168
+Epoch [5], train_loss: 0.173121, val_loss: 0.173566, val_acc: 8.105501
+Epoch [6], train_loss: 0.167777, val_loss: 0.168151, val_acc: 8.660990
+Epoch [7], train_loss: 0.162897, val_loss: 0.164130, val_acc: 9.105319
+Epoch [8], train_loss: 0.158426, val_loss: 0.162696, val_acc: 9.387288
+Epoch [9], train_loss: 0.154543, val_loss: 0.158070, val_acc: 9.881555
+Epoch [10], train_loss: 0.151150, val_loss: 0.153544, val_acc: 10.367150
+Epoch [11], train_loss: 0.148166, val_loss: 0.151436, val_acc: 10.671982
+Epoch [12], train_loss: 0.145547, val_loss: 0.148479, val_acc: 11.039873
+Epoch [13], train_loss: 0.143202, val_loss: 0.144999, val_acc: 11.432967
+Epoch [14], train_loss: 0.141172, val_loss: 0.144491, val_acc: 11.643104
+Epoch [15], train_loss: 0.139237, val_loss: 0.140931, val_acc: 11.967389
+Epoch [16], train_loss: 0.137408, val_loss: 0.138670, val_acc: 12.333000
+Epoch [17], train_loss: 0.135662, val_loss: 0.137552, val_acc: 12.520663
+Epoch [18], train_loss: 0.134055, val_loss: 0.134587, val_acc: 12.855623
+Epoch [19], train_loss: 0.132481, val_loss: 0.132438, val_acc: 13.121663
+Epoch [20], train_loss: 0.131014, val_loss: 0.132134, val_acc: 13.277859
+Epoch [21], train_loss: 0.129596, val_loss: 0.129965, val_acc: 13.509139
+Epoch [22], train_loss: 0.128244, val_loss: 0.130248, val_acc: 13.599520
+Epoch [23], train_loss: 0.126913, val_loss: 0.128946, val_acc: 13.747045
+Epoch [24], train_loss: 0.125653, val_loss: 0.125902, val_acc: 14.098838
+Epoch [25], train_loss: 0.124404, val_loss: 0.124423, val_acc: 14.323063
+Epoch [26], train_loss: 0.123246, val_loss: 0.122960, val_acc: 14.489232
+Epoch [27], train_loss: 0.121968, val_loss: 0.123086, val_acc: 14.665746
+Epoch [28], train_loss: 0.120787, val_loss: 0.119768, val_acc: 14.999456
+Epoch [29], train_loss: 0.119645, val_loss: 0.120132, val_acc: 15.026198
+Epoch [30], train_loss: 0.118475, val_loss: 0.119020, val_acc: 15.115320
+Epoch [31], train_loss: 0.117303, val_loss: 0.117860, val_acc: 15.403120
+Epoch [32], train_loss: 0.116165, val_loss: 0.116273, val_acc: 15.678577
+Epoch [33], train_loss: 0.115085, val_loss: 0.114890, val_acc: 15.820645
+Epoch [34], train_loss: 0.113968, val_loss: 0.114143, val_acc: 15.959746
+Epoch [35], train_loss: 0.112945, val_loss: 0.112560, val_acc: 16.181656
+Epoch [36], train_loss: 0.111905, val_loss: 0.112538, val_acc: 16.294285
+Epoch [37], train_loss: 0.110907, val_loss: 0.109898, val_acc: 16.574314
+Epoch [38], train_loss: 0.109928, val_loss: 0.110502, val_acc: 16.635256
+Epoch [39], train_loss: 0.108889, val_loss: 0.107599, val_acc: 16.973480
+Epoch [40], train_loss: 0.107847, val_loss: 0.110667, val_acc: 16.804647
+Epoch [41], train_loss: 0.106833, val_loss: 0.106607, val_acc: 17.269733
+Epoch [42], train_loss: 0.105909, val_loss: 0.106464, val_acc: 17.275848
+Epoch [43], train_loss: 0.105073, val_loss: 0.103821, val_acc: 17.784788
+Epoch [44], train_loss: 0.104227, val_loss: 0.104774, val_acc: 17.650612
+Epoch [45], train_loss: 0.103392, val_loss: 0.104588, val_acc: 17.807560
+Epoch [46], train_loss: 0.102540, val_loss: 0.103034, val_acc: 17.962812
+Epoch [47], train_loss: 0.101779, val_loss: 0.102854, val_acc: 18.075623
+Epoch [48], train_loss: 0.101025, val_loss: 0.098684, val_acc: 18.501520
+Epoch [49], train_loss: 0.100240, val_loss: 0.101746, val_acc: 18.348545
+Epoch [50], train_loss: 0.099542, val_loss: 0.099614, val_acc: 18.421392
+Epoch [51], train_loss: 0.098781, val_loss: 0.100248, val_acc: 18.569143
+Epoch [52], train_loss: 0.098094, val_loss: 0.100667, val_acc: 18.563803
+Epoch [53], train_loss: 0.097397, val_loss: 0.096893, val_acc: 18.832020
+Epoch [54], train_loss: 0.096738, val_loss: 0.099931, val_acc: 18.699213
+Epoch [55], train_loss: 0.096077, val_loss: 0.096779, val_acc: 19.149368
+Epoch [56], train_loss: 0.095456, val_loss: 0.098727, val_acc: 18.948242
+Epoch [57], train_loss: 0.094812, val_loss: 0.099298, val_acc: 19.071377
+Epoch [58], train_loss: 0.094258, val_loss: 0.098167, val_acc: 19.091124
+Epoch [59], train_loss: 0.093607, val_loss: 0.096382, val_acc: 19.458773
+Epoch [60], train_loss: 0.093029, val_loss: 0.094363, val_acc: 19.627119
+Epoch [61], train_loss: 0.092410, val_loss: 0.092911, val_acc: 19.844511
+Epoch [62], train_loss: 0.091751, val_loss: 0.091761, val_acc: 19.979578
+Epoch [63], train_loss: 0.091235, val_loss: 0.094332, val_acc: 19.899387
+Epoch [64], train_loss: 0.090709, val_loss: 0.095386, val_acc: 19.726013
+Epoch [65], train_loss: 0.090150, val_loss: 0.090982, val_acc: 20.276419
+Epoch [66], train_loss: 0.089613, val_loss: 0.090498, val_acc: 20.364618
+Epoch [67], train_loss: 0.089104, val_loss: 0.088249, val_acc: 20.528696
+Epoch [68], train_loss: 0.088662, val_loss: 0.084446, val_acc: 20.811728
+Epoch [69], train_loss: 0.088117, val_loss: 0.089951, val_acc: 20.492310
+Epoch [70], train_loss: 0.087677, val_loss: 0.089350, val_acc: 20.401463
+Epoch [71], train_loss: 0.087182, val_loss: 0.090564, val_acc: 20.297340
+Epoch [72], train_loss: 0.086655, val_loss: 0.089380, val_acc: 20.621029
+Epoch [73], train_loss: 0.086124, val_loss: 0.087992, val_acc: 20.811457
+Epoch [74], train_loss: 0.085719, val_loss: 0.089389, val_acc: 20.642960
+Epoch [75], train_loss: 0.085298, val_loss: 0.087104, val_acc: 20.865269
+Epoch [76], train_loss: 0.084858, val_loss: 0.084721, val_acc: 21.320906
+Epoch [77], train_loss: 0.084412, val_loss: 0.086465, val_acc: 21.083797
+Epoch [78], train_loss: 0.083912, val_loss: 0.083116, val_acc: 21.468422
+Epoch [79], train_loss: 0.083555, val_loss: 0.085852, val_acc: 21.232246
+Epoch [80], train_loss: 0.083101, val_loss: 0.083501, val_acc: 21.486906
+Epoch [81], train_loss: 0.082824, val_loss: 0.083941, val_acc: 21.235981
+Epoch [82], train_loss: 0.082381, val_loss: 0.080654, val_acc: 21.783527
+Epoch [83], train_loss: 0.081957, val_loss: 0.081785, val_acc: 21.738005
+Epoch [84], train_loss: 0.081578, val_loss: 0.080454, val_acc: 21.776960
+Epoch [85], train_loss: 0.081257, val_loss: 0.083010, val_acc: 21.626421
+Epoch [86], train_loss: 0.080882, val_loss: 0.085027, val_acc: 21.487967
+Epoch [87], train_loss: 0.080524, val_loss: 0.079179, val_acc: 21.981812
+Epoch [88], train_loss: 0.080291, val_loss: 0.082787, val_acc: 21.602827
+Epoch [89], train_loss: 0.079919, val_loss: 0.081075, val_acc: 21.970722
+Epoch [90], train_loss: 0.079574, val_loss: 0.078419, val_acc: 22.083481
+Epoch [91], train_loss: 0.079214, val_loss: 0.078737, val_acc: 22.057064
+Epoch [92], train_loss: 0.078902, val_loss: 0.079216, val_acc: 21.990189
+Epoch [93], train_loss: 0.078701, val_loss: 0.079688, val_acc: 22.133158
+Epoch [94], train_loss: 0.078341, val_loss: 0.080411, val_acc: 22.081230
+Epoch [95], train_loss: 0.077981, val_loss: 0.079533, val_acc: 22.150908
+Epoch [96], train_loss: 0.077719, val_loss: 0.080235, val_acc: 22.089252
+Epoch [97], train_loss: 0.077470, val_loss: 0.077726, val_acc: 22.373716
+Epoch [98], train_loss: 0.077220, val_loss: 0.078994, val_acc: 22.300293
+Epoch [99], train_loss: 0.076921, val_loss: 0.079273, val_acc: 22.263401
+Epoch [100], train_loss: 0.076561, val_loss: 0.077377, val_acc: 22.497238
+Epoch [101], train_loss: 0.076361, val_loss: 0.077216, val_acc: 22.525692
+Epoch [102], train_loss: 0.076113, val_loss: 0.076206, val_acc: 22.598078
+Epoch [103], train_loss: 0.075725, val_loss: 0.077315, val_acc: 22.536283
+Epoch [104], train_loss: 0.075583, val_loss: 0.078944, val_acc: 22.324186
+Epoch [105], train_loss: 0.075450, val_loss: 0.073758, val_acc: 22.831192
+Epoch [106], train_loss: 0.075055, val_loss: 0.075953, val_acc: 22.674553
+Epoch [107], train_loss: 0.074740, val_loss: 0.075753, val_acc: 22.621294
+Epoch [108], train_loss: 0.074539, val_loss: 0.077430, val_acc: 22.443186
+Epoch [109], train_loss: 0.074265, val_loss: 0.072961, val_acc: 22.932257
+Epoch [110], train_loss: 0.074017, val_loss: 0.073989, val_acc: 22.923866
+Epoch [111], train_loss: 0.073747, val_loss: 0.074644, val_acc: 22.839310
+Epoch [112], train_loss: 0.073523, val_loss: 0.072499, val_acc: 23.072340
+Epoch [113], train_loss: 0.073420, val_loss: 0.075559, val_acc: 22.775639
+Epoch [114], train_loss: 0.073120, val_loss: 0.073606, val_acc: 22.884357
+Epoch [115], train_loss: 0.072872, val_loss: 0.073450, val_acc: 22.902931
+Epoch [116], train_loss: 0.072707, val_loss: 0.071828, val_acc: 23.074425
+Epoch [117], train_loss: 0.072471, val_loss: 0.074651, val_acc: 22.921873
+Epoch [118], train_loss: 0.072223, val_loss: 0.070970, val_acc: 23.162195
+Epoch [119], train_loss: 0.072018, val_loss: 0.071577, val_acc: 23.074120
+Epoch [120], train_loss: 0.071718, val_loss: 0.069477, val_acc: 23.423820
+Epoch [121], train_loss: 0.071582, val_loss: 0.073309, val_acc: 23.108259
+Epoch [122], train_loss: 0.071350, val_loss: 0.071220, val_acc: 23.273796
+Epoch [123], train_loss: 0.071208, val_loss: 0.071294, val_acc: 23.306463
+Epoch [124], train_loss: 0.070929, val_loss: 0.071930, val_acc: 23.124855
+Epoch [125], train_loss: 0.070796, val_loss: 0.069632, val_acc: 23.273911
+Epoch [126], train_loss: 0.070502, val_loss: 0.070310, val_acc: 23.255367
+Epoch [127], train_loss: 0.070387, val_loss: 0.070342, val_acc: 23.396896
+Epoch [128], train_loss: 0.070162, val_loss: 0.069470, val_acc: 23.496124
+Epoch [129], train_loss: 0.070022, val_loss: 0.071085, val_acc: 23.298182
+Epoch [130], train_loss: 0.069857, val_loss: 0.070485, val_acc: 23.322102
+Epoch [131], train_loss: 0.069600, val_loss: 0.069502, val_acc: 23.485361
+Epoch [132], train_loss: 0.069332, val_loss: 0.070928, val_acc: 23.250759
+Epoch [133], train_loss: 0.069275, val_loss: 0.070824, val_acc: 23.358953
+Epoch [134], train_loss: 0.069048, val_loss: 0.069620, val_acc: 23.344013
+Epoch [135], train_loss: 0.068855, val_loss: 0.069437, val_acc: 23.498114
+Epoch [136], train_loss: 0.068715, val_loss: 0.071036, val_acc: 23.235308
+Epoch [137], train_loss: 0.068519, val_loss: 0.070008, val_acc: 23.457230
+Epoch [138], train_loss: 0.068375, val_loss: 0.068575, val_acc: 23.520222
+Epoch [139], train_loss: 0.068125, val_loss: 0.068210, val_acc: 23.549513
+Epoch [140], train_loss: 0.067982, val_loss: 0.068791, val_acc: 23.451649
+Epoch [141], train_loss: 0.067862, val_loss: 0.071825, val_acc: 23.248692
+Epoch [142], train_loss: 0.067716, val_loss: 0.069825, val_acc: 23.511528
+Epoch [143], train_loss: 0.067476, val_loss: 0.067705, val_acc: 23.647863
+Epoch [144], train_loss: 0.067290, val_loss: 0.069018, val_acc: 23.490221
+Epoch [145], train_loss: 0.067172, val_loss: 0.068175, val_acc: 23.557560
+Epoch [146], train_loss: 0.066984, val_loss: 0.066462, val_acc: 23.701262
+Epoch [147], train_loss: 0.066773, val_loss: 0.067666, val_acc: 23.641768
+Epoch [148], train_loss: 0.066743, val_loss: 0.068244, val_acc: 23.570707
+Epoch [149], train_loss: 0.066545, val_loss: 0.068054, val_acc: 23.522814
+Epoch [150], train_loss: 0.066396, val_loss: 0.067267, val_acc: 23.611427
+Epoch [151], train_loss: 0.066244, val_loss: 0.067510, val_acc: 23.597071
+Epoch [152], train_loss: 0.066107, val_loss: 0.067235, val_acc: 23.508747
+Epoch [153], train_loss: 0.065940, val_loss: 0.066482, val_acc: 23.713770
+Epoch [154], train_loss: 0.065751, val_loss: 0.067999, val_acc: 23.515081
+Epoch [155], train_loss: 0.065577, val_loss: 0.065379, val_acc: 23.697001
+Epoch [156], train_loss: 0.065461, val_loss: 0.065783, val_acc: 23.698078
+Epoch [157], train_loss: 0.065311, val_loss: 0.065549, val_acc: 23.720808
+Epoch [158], train_loss: 0.065287, val_loss: 0.066752, val_acc: 23.633606
+Epoch [159], train_loss: 0.065042, val_loss: 0.066374, val_acc: 23.651800
+Epoch [160], train_loss: 0.064861, val_loss: 0.065997, val_acc: 23.721300
+Epoch [161], train_loss: 0.064776, val_loss: 0.065773, val_acc: 23.607164
+Epoch [162], train_loss: 0.064666, val_loss: 0.066275, val_acc: 23.533720
+Epoch [163], train_loss: 0.064537, val_loss: 0.065624, val_acc: 23.713163
+Epoch [164], train_loss: 0.064259, val_loss: 0.065585, val_acc: 23.638319
+Epoch [165], train_loss: 0.064233, val_loss: 0.064404, val_acc: 23.839506
+Epoch [166], train_loss: 0.064074, val_loss: 0.064250, val_acc: 23.807316
+Epoch [167], train_loss: 0.063990, val_loss: 0.066130, val_acc: 23.662485
+Epoch [168], train_loss: 0.063754, val_loss: 0.064941, val_acc: 23.738020
+Epoch [169], train_loss: 0.063712, val_loss: 0.065025, val_acc: 23.708408
+Epoch [170], train_loss: 0.063510, val_loss: 0.065267, val_acc: 23.654062
+Epoch [171], train_loss: 0.063415, val_loss: 0.066543, val_acc: 23.583313
+Epoch [172], train_loss: 0.063244, val_loss: 0.064486, val_acc: 23.707962
+Epoch [173], train_loss: 0.063213, val_loss: 0.064930, val_acc: 23.687159
+Epoch [174], train_loss: 0.063004, val_loss: 0.064433, val_acc: 23.716898
+Epoch [175], train_loss: 0.062896, val_loss: 0.064671, val_acc: 23.736677
+Epoch [176], train_loss: 0.062776, val_loss: 0.063568, val_acc: 23.843399
+Epoch [177], train_loss: 0.062647, val_loss: 0.063884, val_acc: 23.751541
+Epoch [178], train_loss: 0.062554, val_loss: 0.065972, val_acc: 23.620804
+Epoch [179], train_loss: 0.062437, val_loss: 0.064110, val_acc: 23.653364
+Epoch [180], train_loss: 0.062356, val_loss: 0.065316, val_acc: 23.607441
+Epoch [181], train_loss: 0.062194, val_loss: 0.063811, val_acc: 23.707676
+Epoch [182], train_loss: 0.062057, val_loss: 0.063740, val_acc: 23.793390
+Epoch [183], train_loss: 0.062007, val_loss: 0.063771, val_acc: 23.784796
+Epoch [184], train_loss: 0.061847, val_loss: 0.062933, val_acc: 23.791101
+Epoch [185], train_loss: 0.061741, val_loss: 0.062730, val_acc: 23.792751
+Epoch [186], train_loss: 0.061586, val_loss: 0.062876, val_acc: 23.766937
+Epoch [187], train_loss: 0.061490, val_loss: 0.063107, val_acc: 23.749830
+Epoch [188], train_loss: 0.061425, val_loss: 0.063932, val_acc: 23.765076
+Epoch [189], train_loss: 0.061326, val_loss: 0.063622, val_acc: 23.751432
+Epoch [190], train_loss: 0.061198, val_loss: 0.064128, val_acc: 23.724369
+Epoch [191], train_loss: 0.061092, val_loss: 0.063074, val_acc: 23.735569
+Epoch [192], train_loss: 0.060960, val_loss: 0.062977, val_acc: 23.707930
+Epoch [193], train_loss: 0.060919, val_loss: 0.064192, val_acc: 23.684862
+Epoch [194], train_loss: 0.060774, val_loss: 0.064083, val_acc: 23.696167
+Epoch [195], train_loss: 0.060616, val_loss: 0.062862, val_acc: 23.789690
+Epoch [196], train_loss: 0.060586, val_loss: 0.063076, val_acc: 23.771240
+Epoch [197], train_loss: 0.060480, val_loss: 0.062530, val_acc: 23.714396
+Epoch [198], train_loss: 0.060488, val_loss: 0.062629, val_acc: 23.756592
+Epoch [199], train_loss: 0.060222, val_loss: 0.063050, val_acc: 23.708235
+Epoch [200], train_loss: 0.060201, val_loss: 0.063031, val_acc: 23.755215
+Epoch [201], train_loss: 0.060182, val_loss: 0.062511, val_acc: 23.739878
+Epoch [202], train_loss: 0.060062, val_loss: 0.062543, val_acc: 23.766579
+Epoch [203], train_loss: 0.059923, val_loss: 0.062637, val_acc: 23.693714
+Epoch [204], train_loss: 0.059821, val_loss: 0.062983, val_acc: 23.713354
+Epoch [205], train_loss: 0.059802, val_loss: 0.062245, val_acc: 23.739660
+Epoch [206], train_loss: 0.059713, val_loss: 0.062746, val_acc: 23.731066
+Epoch [207], train_loss: 0.059565, val_loss: 0.063013, val_acc: 23.659674
+Epoch [208], train_loss: 0.059532, val_loss: 0.062373, val_acc: 23.742455
+Epoch [209], train_loss: 0.059479, val_loss: 0.062746, val_acc: 23.744841
+Epoch [210], train_loss: 0.059331, val_loss: 0.062241, val_acc: 23.742395
+Epoch [211], train_loss: 0.059235, val_loss: 0.062616, val_acc: 23.750618
+Epoch [212], train_loss: 0.059188, val_loss: 0.063552, val_acc: 23.696152
+Epoch [213], train_loss: 0.059114, val_loss: 0.062845, val_acc: 23.628578
+Epoch [214], train_loss: 0.059015, val_loss: 0.062478, val_acc: 23.697590
+Epoch [215], train_loss: 0.058904, val_loss: 0.062946, val_acc: 23.662260
+Epoch [216], train_loss: 0.058877, val_loss: 0.062151, val_acc: 23.698408
+Epoch [217], train_loss: 0.058736, val_loss: 0.062867, val_acc: 23.648695
+Epoch [218], train_loss: 0.058701, val_loss: 0.062104, val_acc: 23.717255
+Epoch [219], train_loss: 0.058716, val_loss: 0.062788, val_acc: 23.682606
+Epoch [220], train_loss: 0.058531, val_loss: 0.062388, val_acc: 23.690214
+Epoch [221], train_loss: 0.058502, val_loss: 0.062266, val_acc: 23.683571
+Epoch [222], train_loss: 0.058459, val_loss: 0.061975, val_acc: 23.702044
+Epoch [223], train_loss: 0.058346, val_loss: 0.062156, val_acc: 23.634823
+Epoch [224], train_loss: 0.058331, val_loss: 0.061660, val_acc: 23.696695
+Epoch [225], train_loss: 0.058172, val_loss: 0.062210, val_acc: 23.615221
+Epoch [226], train_loss: 0.058121, val_loss: 0.061910, val_acc: 23.690744
+Epoch [227], train_loss: 0.058062, val_loss: 0.061572, val_acc: 23.641060
+Epoch [228], train_loss: 0.057989, val_loss: 0.062020, val_acc: 23.720768
+Epoch [229], train_loss: 0.057965, val_loss: 0.061869, val_acc: 23.643152
+Epoch [230], train_loss: 0.057822, val_loss: 0.061600, val_acc: 23.680416
+Epoch [231], train_loss: 0.057816, val_loss: 0.061642, val_acc: 23.710945
+Epoch [232], train_loss: 0.057802, val_loss: 0.061407, val_acc: 23.712681
+Epoch [233], train_loss: 0.057690, val_loss: 0.061848, val_acc: 23.723261
+Epoch [234], train_loss: 0.057632, val_loss: 0.061753, val_acc: 23.619917
+Epoch [235], train_loss: 0.057567, val_loss: 0.061740, val_acc: 23.667881
+Epoch [236], train_loss: 0.057583, val_loss: 0.061928, val_acc: 23.672279
+Epoch [237], train_loss: 0.057530, val_loss: 0.061827, val_acc: 23.642408
+Epoch [238], train_loss: 0.057450, val_loss: 0.061541, val_acc: 23.568247
+Epoch [239], train_loss: 0.057451, val_loss: 0.062531, val_acc: 23.522068
+Epoch [240], train_loss: 0.057289, val_loss: 0.061561, val_acc: 23.651518
+Epoch [241], train_loss: 0.057276, val_loss: 0.061771, val_acc: 23.603340
+Epoch [242], train_loss: 0.057277, val_loss: 0.062104, val_acc: 23.617624
+Epoch [243], train_loss: 0.057154, val_loss: 0.061474, val_acc: 23.661024
+Epoch [244], train_loss: 0.057104, val_loss: 0.061979, val_acc: 23.587370
+Epoch [245], train_loss: 0.056971, val_loss: 0.061387, val_acc: 23.663458
+Epoch [246], train_loss: 0.057048, val_loss: 0.061532, val_acc: 23.711073
+Epoch [247], train_loss: 0.056983, val_loss: 0.061674, val_acc: 23.609638
+Epoch [248], train_loss: 0.056902, val_loss: 0.061635, val_acc: 23.590775
+Epoch [249], train_loss: 0.056861, val_loss: 0.061323, val_acc: 23.590784
+Epoch [250], train_loss: 0.056729, val_loss: 0.061656, val_acc: 23.662352
+Epoch [251], train_loss: 0.056743, val_loss: 0.061405, val_acc: 23.597248
+Epoch [252], train_loss: 0.056691, val_loss: 0.062304, val_acc: 23.598434
+Epoch [253], train_loss: 0.057102, val_loss: 0.061678, val_acc: 23.489851
+Epoch [254], train_loss: 0.056821, val_loss: 0.061368, val_acc: 23.488794
+Epoch [255], train_loss: 0.056636, val_loss: 0.061494, val_acc: 23.611427
+Epoch [256], train_loss: 0.056593, val_loss: 0.061357, val_acc: 23.633583
+Epoch [257], train_loss: 0.056504, val_loss: 0.061200, val_acc: 23.570116
+Epoch [258], train_loss: 0.056515, val_loss: 0.061367, val_acc: 23.590521
+Epoch [259], train_loss: 0.056479, val_loss: 0.061408, val_acc: 23.499199
+Epoch [260], train_loss: 0.056457, val_loss: 0.061245, val_acc: 23.517099
+Epoch [261], train_loss: 0.056455, val_loss: 0.061334, val_acc: 23.654270
+Epoch [262], train_loss: 0.056347, val_loss: 0.061318, val_acc: 23.446388
+Epoch [263], train_loss: 0.056274, val_loss: 0.061224, val_acc: 23.649635
+Epoch [264], train_loss: 0.056296, val_loss: 0.061660, val_acc: 23.502481
+Epoch [265], train_loss: 0.056260, val_loss: 0.061611, val_acc: 23.545019
+Epoch [266], train_loss: 0.056218, val_loss: 0.061441, val_acc: 23.544661
+Epoch [267], train_loss: 0.056213, val_loss: 0.061450, val_acc: 23.592436
+Epoch [268], train_loss: 0.056148, val_loss: 0.061242, val_acc: 23.502808
+Epoch [269], train_loss: 0.056111, val_loss: 0.061159, val_acc: 23.625921
+Epoch [270], train_loss: 0.056096, val_loss: 0.061617, val_acc: 23.574614
+Epoch [271], train_loss: 0.056031, val_loss: 0.061073, val_acc: 23.494484
+Epoch [272], train_loss: 0.055964, val_loss: 0.061454, val_acc: 23.432762
+Epoch [273], train_loss: 0.056004, val_loss: 0.061605, val_acc: 23.513578
+Epoch [274], train_loss: 0.055954, val_loss: 0.061505, val_acc: 23.449308
+Epoch [275], train_loss: 0.055948, val_loss: 0.061138, val_acc: 23.613474
+Epoch [276], train_loss: 0.055867, val_loss: 0.061301, val_acc: 23.448778
+Epoch [277], train_loss: 0.055799, val_loss: 0.061365, val_acc: 23.523037
+Epoch [278], train_loss: 0.055811, val_loss: 0.061327, val_acc: 23.450653
+Epoch [279], train_loss: 0.055763, val_loss: 0.061236, val_acc: 23.525047
+Epoch [280], train_loss: 0.055798, val_loss: 0.061176, val_acc: 23.553257
+Epoch [281], train_loss: 0.055717, val_loss: 0.060924, val_acc: 23.512028
+Epoch [282], train_loss: 0.055704, val_loss: 0.061391, val_acc: 23.379066
+Epoch [283], train_loss: 0.055677, val_loss: 0.061096, val_acc: 23.456814
+Epoch [284], train_loss: 0.055780, val_loss: 0.061127, val_acc: 23.446089
+Epoch [285], train_loss: 0.055712, val_loss: 0.061128, val_acc: 23.437580
+Epoch [286], train_loss: 0.055668, val_loss: 0.061288, val_acc: 23.577450
+Epoch [287], train_loss: 0.055632, val_loss: 0.061079, val_acc: 23.483330
+Epoch [288], train_loss: 0.055593, val_loss: 0.061112, val_acc: 23.514462
+Epoch [289], train_loss: 0.055562, val_loss: 0.061193, val_acc: 23.553463
+Epoch [290], train_loss: 0.055545, val_loss: 0.061337, val_acc: 23.531683
+Epoch [291], train_loss: 0.055496, val_loss: 0.061136, val_acc: 23.558359
+Epoch [292], train_loss: 0.055462, val_loss: 0.061342, val_acc: 23.474831
+Epoch [293], train_loss: 0.055449, val_loss: 0.061274, val_acc: 23.468098
+Epoch [294], train_loss: 0.055450, val_loss: 0.061051, val_acc: 23.488256
+Epoch [295], train_loss: 0.055378, val_loss: 0.061039, val_acc: 23.405870
+Epoch [296], train_loss: 0.055364, val_loss: 0.061421, val_acc: 23.342575
+Epoch [297], train_loss: 0.055381, val_loss: 0.061208, val_acc: 23.513271
+Epoch [298], train_loss: 0.055346, val_loss: 0.061325, val_acc: 23.375349
+Epoch [299], train_loss: 0.055379, val_loss: 0.061250, val_acc: 23.590075
+Epoch [300], train_loss: 0.055284, val_loss: 0.060998, val_acc: 23.459892
+Epoch [301], train_loss: 0.055236, val_loss: 0.061083, val_acc: 23.495520
+Epoch [302], train_loss: 0.055278, val_loss: 0.061225, val_acc: 23.479393
+Epoch [303], train_loss: 0.055173, val_loss: 0.061050, val_acc: 23.507151
+Epoch [304], train_loss: 0.055172, val_loss: 0.061112, val_acc: 23.359169
+Epoch [305], train_loss: 0.055185, val_loss: 0.061132, val_acc: 23.522181
+Epoch [306], train_loss: 0.055134, val_loss: 0.061146, val_acc: 23.404570
+Epoch [307], train_loss: 0.055105, val_loss: 0.061097, val_acc: 23.346699
+Epoch [308], train_loss: 0.055101, val_loss: 0.061085, val_acc: 23.405212
+Epoch [309], train_loss: 0.055092, val_loss: 0.061257, val_acc: 23.357296
+Epoch [310], train_loss: 0.055042, val_loss: 0.061166, val_acc: 23.286772
+Epoch [311], train_loss: 0.055105, val_loss: 0.061012, val_acc: 23.565271
+Epoch [312], train_loss: 0.054987, val_loss: 0.061193, val_acc: 23.365608
+Epoch [313], train_loss: 0.054939, val_loss: 0.061218, val_acc: 23.401640
+Epoch [314], train_loss: 0.054963, val_loss: 0.061264, val_acc: 23.318712
+Epoch [315], train_loss: 0.054949, val_loss: 0.061079, val_acc: 23.471531
+Epoch [316], train_loss: 0.055156, val_loss: 0.061032, val_acc: 23.432142
+Epoch [317], train_loss: 0.055093, val_loss: 0.061103, val_acc: 23.402067
+Epoch [318], train_loss: 0.054957, val_loss: 0.061017, val_acc: 23.475437
+Epoch [319], train_loss: 0.054897, val_loss: 0.061101, val_acc: 23.498344
+Epoch [320], train_loss: 0.054932, val_loss: 0.061113, val_acc: 23.389750
+Epoch [321], train_loss: 0.054942, val_loss: 0.061395, val_acc: 23.245676
+Epoch [322], train_loss: 0.054851, val_loss: 0.061004, val_acc: 23.444763
+Epoch [323], train_loss: 0.054867, val_loss: 0.061271, val_acc: 23.231709
+Epoch [324], train_loss: 0.054810, val_loss: 0.061050, val_acc: 23.449812
+Epoch [325], train_loss: 0.054823, val_loss: 0.061100, val_acc: 23.307331
+Epoch [326], train_loss: 0.054771, val_loss: 0.061142, val_acc: 23.370750
+Epoch [327], train_loss: 0.054828, val_loss: 0.061474, val_acc: 23.428877
+Epoch [328], train_loss: 0.054759, val_loss: 0.061177, val_acc: 23.327274
+Epoch [329], train_loss: 0.054796, val_loss: 0.061355, val_acc: 23.346582
+Epoch [330], train_loss: 0.054696, val_loss: 0.060940, val_acc: 23.407011
+Epoch [331], train_loss: 0.054726, val_loss: 0.061151, val_acc: 23.453335
+Epoch [332], train_loss: 0.054687, val_loss: 0.061036, val_acc: 23.437515
+Epoch [333], train_loss: 0.054682, val_loss: 0.061395, val_acc: 23.298374
+Epoch [334], train_loss: 0.054619, val_loss: 0.061108, val_acc: 23.351194
+Epoch [335], train_loss: 0.054703, val_loss: 0.061275, val_acc: 23.157480
+Epoch [336], train_loss: 0.054649, val_loss: 0.061137, val_acc: 23.308146
+Epoch [337], train_loss: 0.054635, val_loss: 0.061002, val_acc: 23.358025
+Epoch [338], train_loss: 0.054600, val_loss: 0.061214, val_acc: 23.471357
+Epoch [339], train_loss: 0.054528, val_loss: 0.061067, val_acc: 23.340143
+Epoch [340], train_loss: 0.054579, val_loss: 0.061139, val_acc: 23.397602
+Epoch [341], train_loss: 0.054581, val_loss: 0.061061, val_acc: 23.458881
+Epoch [342], train_loss: 0.054535, val_loss: 0.061188, val_acc: 23.325468
+Epoch [343], train_loss: 0.054551, val_loss: 0.061029, val_acc: 23.409950
+Epoch [344], train_loss: 0.054505, val_loss: 0.061295, val_acc: 23.305058
+Epoch [345], train_loss: 0.054430, val_loss: 0.061175, val_acc: 23.386650
+Epoch [346], train_loss: 0.054508, val_loss: 0.061126, val_acc: 23.276527
+Epoch [347], train_loss: 0.054483, val_loss: 0.061194, val_acc: 23.366302
+Epoch [348], train_loss: 0.054420, val_loss: 0.061031, val_acc: 23.449406
+Epoch [349], train_loss: 0.054428, val_loss: 0.061128, val_acc: 23.326666
+Epoch [350], train_loss: 0.054427, val_loss: 0.061035, val_acc: 23.435394
+Epoch [351], train_loss: 0.054394, val_loss: 0.061076, val_acc: 23.340103
+Epoch [352], train_loss: 0.054361, val_loss: 0.061235, val_acc: 23.278223
+Epoch [353], train_loss: 0.054344, val_loss: 0.060991, val_acc: 23.417559
+Epoch [354], train_loss: 0.054364, val_loss: 0.061040, val_acc: 23.327890
+Epoch [355], train_loss: 0.054586, val_loss: 0.061317, val_acc: 23.434162
+Epoch [356], train_loss: 0.054604, val_loss: 0.061363, val_acc: 23.224949
+Epoch [357], train_loss: 0.054368, val_loss: 0.061138, val_acc: 23.211271
+Epoch [358], train_loss: 0.054377, val_loss: 0.061336, val_acc: 23.165337
+Epoch [359], train_loss: 0.054284, val_loss: 0.061103, val_acc: 23.349199
+Epoch [360], train_loss: 0.054275, val_loss: 0.061007, val_acc: 23.356066
+Epoch [361], train_loss: 0.054281, val_loss: 0.061175, val_acc: 23.256916
+Epoch [362], train_loss: 0.054244, val_loss: 0.061060, val_acc: 23.422037
+Epoch [363], train_loss: 0.054249, val_loss: 0.061179, val_acc: 23.300066
+Epoch [364], train_loss: 0.054286, val_loss: 0.061092, val_acc: 23.449326
+Epoch [365], train_loss: 0.054196, val_loss: 0.061197, val_acc: 23.295975
+Epoch [366], train_loss: 0.054289, val_loss: 0.061267, val_acc: 23.255476
+Epoch [367], train_loss: 0.054235, val_loss: 0.061034, val_acc: 23.364925
+Epoch [368], train_loss: 0.054263, val_loss: 0.060998, val_acc: 23.370056
+Epoch [369], train_loss: 0.054150, val_loss: 0.061128, val_acc: 23.398949
+Epoch [370], train_loss: 0.054098, val_loss: 0.061017, val_acc: 23.336729
+Epoch [371], train_loss: 0.054153, val_loss: 0.060992, val_acc: 23.361328
+Epoch [372], train_loss: 0.054166, val_loss: 0.061151, val_acc: 23.366756
+Epoch [373], train_loss: 0.054148, val_loss: 0.060944, val_acc: 23.320402
+Epoch [374], train_loss: 0.054053, val_loss: 0.061178, val_acc: 23.244625
+Epoch [375], train_loss: 0.054089, val_loss: 0.061092, val_acc: 23.380058
+Epoch [376], train_loss: 0.054057, val_loss: 0.061403, val_acc: 23.222782
+Epoch [377], train_loss: 0.054070, val_loss: 0.061099, val_acc: 23.319305
+Epoch [378], train_loss: 0.054055, val_loss: 0.061085, val_acc: 23.314941
+Epoch [379], train_loss: 0.054060, val_loss: 0.061106, val_acc: 23.253977
+Epoch [380], train_loss: 0.054019, val_loss: 0.060992, val_acc: 23.300890
+Epoch [381], train_loss: 0.054004, val_loss: 0.061338, val_acc: 23.243729
+Epoch [382], train_loss: 0.053959, val_loss: 0.061231, val_acc: 23.220821
+Epoch [383], train_loss: 0.054012, val_loss: 0.061296, val_acc: 23.260504
+Epoch [384], train_loss: 0.053958, val_loss: 0.061250, val_acc: 23.213358
+Epoch [385], train_loss: 0.053990, val_loss: 0.061287, val_acc: 23.232523
+Epoch [386], train_loss: 0.053961, val_loss: 0.061097, val_acc: 23.369230
+Epoch [387], train_loss: 0.053889, val_loss: 0.061042, val_acc: 23.325226
+Epoch [388], train_loss: 0.053852, val_loss: 0.061233, val_acc: 23.273333
+Epoch [389], train_loss: 0.053904, val_loss: 0.061180, val_acc: 23.241978
+Epoch [390], train_loss: 0.053885, val_loss: 0.061188, val_acc: 23.222309
+Epoch [391], train_loss: 0.053854, val_loss: 0.061239, val_acc: 23.327734
+Epoch [392], train_loss: 0.054436, val_loss: 0.061153, val_acc: 23.300655
+Epoch [393], train_loss: 0.053952, val_loss: 0.061200, val_acc: 23.352545
+Epoch [394], train_loss: 0.053897, val_loss: 0.061082, val_acc: 23.248531
+Epoch [395], train_loss: 0.053868, val_loss: 0.061186, val_acc: 23.313154
+Epoch [396], train_loss: 0.053879, val_loss: 0.061198, val_acc: 23.200687
+Epoch [397], train_loss: 0.053834, val_loss: 0.061083, val_acc: 23.350906
+Epoch [398], train_loss: 0.053837, val_loss: 0.061186, val_acc: 23.334927
+Epoch [399], train_loss: 0.053755, val_loss: 0.061119, val_acc: 23.221937
+Epoch [400], train_loss: 0.053830, val_loss: 0.061089, val_acc: 23.302101
+Epoch [401], train_loss: 0.053791, val_loss: 0.061099, val_acc: 23.347099
+Epoch [402], train_loss: 0.053729, val_loss: 0.061225, val_acc: 23.301777
+Epoch [403], train_loss: 0.053756, val_loss: 0.061125, val_acc: 23.281712
+Epoch [404], train_loss: 0.053727, val_loss: 0.061167, val_acc: 23.208525
+Epoch [405], train_loss: 0.053721, val_loss: 0.061041, val_acc: 23.355925
+Epoch [406], train_loss: 0.053718, val_loss: 0.061020, val_acc: 23.368498
+Epoch [407], train_loss: 0.053666, val_loss: 0.061150, val_acc: 23.284767
+Epoch [408], train_loss: 0.053691, val_loss: 0.061286, val_acc: 23.158192
+Epoch [409], train_loss: 0.053713, val_loss: 0.061319, val_acc: 23.336220
+Epoch [410], train_loss: 0.053686, val_loss: 0.061229, val_acc: 23.185064
+Epoch [411], train_loss: 0.053621, val_loss: 0.061152, val_acc: 23.311937
+Epoch [412], train_loss: 0.053700, val_loss: 0.061165, val_acc: 23.291178
+Epoch [413], train_loss: 0.053697, val_loss: 0.061232, val_acc: 23.251673
+Epoch [414], train_loss: 0.053657, val_loss: 0.061181, val_acc: 23.168110
+Epoch [415], train_loss: 0.053621, val_loss: 0.061267, val_acc: 23.108070
+Epoch [416], train_loss: 0.053561, val_loss: 0.061081, val_acc: 23.242329
+Epoch [417], train_loss: 0.053570, val_loss: 0.061117, val_acc: 23.322411
+Epoch [418], train_loss: 0.053531, val_loss: 0.061148, val_acc: 23.275562
+Epoch [419], train_loss: 0.053584, val_loss: 0.061223, val_acc: 23.183296
+Epoch [420], train_loss: 0.053617, val_loss: 0.061263, val_acc: 23.215145
+Epoch [421], train_loss: 0.053511, val_loss: 0.061288, val_acc: 23.069004
+Epoch [422], train_loss: 0.053491, val_loss: 0.061190, val_acc: 23.280411
+Epoch [423], train_loss: 0.053532, val_loss: 0.061152, val_acc: 23.248743
+Epoch [424], train_loss: 0.053484, val_loss: 0.061518, val_acc: 23.094807
+Epoch [425], train_loss: 0.053538, val_loss: 0.061291, val_acc: 23.218319
+Epoch [426], train_loss: 0.053437, val_loss: 0.061089, val_acc: 23.312317
+Epoch [427], train_loss: 0.053481, val_loss: 0.061541, val_acc: 23.209913
+Epoch [428], train_loss: 0.053484, val_loss: 0.061040, val_acc: 23.306976
+Epoch [429], train_loss: 0.053503, val_loss: 0.061144, val_acc: 23.277430
+Epoch [430], train_loss: 0.053450, val_loss: 0.061360, val_acc: 23.240135
+Epoch [431], train_loss: 0.053428, val_loss: 0.061232, val_acc: 23.276545
+Epoch [432], train_loss: 0.053381, val_loss: 0.061296, val_acc: 23.247129
+Epoch [433], train_loss: 0.053403, val_loss: 0.061208, val_acc: 23.211319
+Epoch [434], train_loss: 0.053412, val_loss: 0.061298, val_acc: 23.195862
+Epoch [435], train_loss: 0.053415, val_loss: 0.061159, val_acc: 23.255934
+Epoch [436], train_loss: 0.053414, val_loss: 0.061167, val_acc: 23.177689
+Epoch [437], train_loss: 0.053402, val_loss: 0.061324, val_acc: 23.262924
+Epoch [438], train_loss: 0.053357, val_loss: 0.061230, val_acc: 23.117319
+Epoch [439], train_loss: 0.053362, val_loss: 0.061252, val_acc: 23.283609
+Epoch [440], train_loss: 0.053367, val_loss: 0.061176, val_acc: 23.284119
+Epoch [441], train_loss: 0.053302, val_loss: 0.061202, val_acc: 23.260197
+Epoch [442], train_loss: 0.053289, val_loss: 0.061094, val_acc: 23.312464
+Epoch [443], train_loss: 0.053306, val_loss: 0.061208, val_acc: 23.261414
+Epoch [444], train_loss: 0.053293, val_loss: 0.061392, val_acc: 23.065300
+Epoch [445], train_loss: 0.053524, val_loss: 0.061045, val_acc: 23.372145
+Epoch [446], train_loss: 0.053458, val_loss: 0.061050, val_acc: 23.276316
+Epoch [447], train_loss: 0.053408, val_loss: 0.061181, val_acc: 23.194532
+Epoch [448], train_loss: 0.053289, val_loss: 0.061345, val_acc: 23.083967
+Epoch [449], train_loss: 0.053278, val_loss: 0.061242, val_acc: 23.209572
+Epoch [450], train_loss: 0.053302, val_loss: 0.061230, val_acc: 23.136156
+Epoch [451], train_loss: 0.053260, val_loss: 0.061285, val_acc: 23.233080
+Epoch [452], train_loss: 0.053215, val_loss: 0.061238, val_acc: 23.274185
+Epoch [453], train_loss: 0.053230, val_loss: 0.061170, val_acc: 23.196070
+Epoch [454], train_loss: 0.053188, val_loss: 0.061147, val_acc: 23.182215
+Epoch [455], train_loss: 0.053303, val_loss: 0.061244, val_acc: 23.206354
+Epoch [456], train_loss: 0.053231, val_loss: 0.061351, val_acc: 23.148689
+Epoch [457], train_loss: 0.053216, val_loss: 0.061198, val_acc: 23.222998
+Epoch [458], train_loss: 0.053145, val_loss: 0.061283, val_acc: 23.193510
+Epoch [459], train_loss: 0.053168, val_loss: 0.061270, val_acc: 23.157907
+Epoch [460], train_loss: 0.053169, val_loss: 0.061184, val_acc: 23.250393
+Epoch [461], train_loss: 0.053129, val_loss: 0.061277, val_acc: 23.168413
+Epoch [462], train_loss: 0.053184, val_loss: 0.061243, val_acc: 23.165573
+Epoch [463], train_loss: 0.053043, val_loss: 0.061266, val_acc: 23.171610
+Epoch [464], train_loss: 0.053099, val_loss: 0.061239, val_acc: 23.121639
+Epoch [465], train_loss: 0.053113, val_loss: 0.061295, val_acc: 23.131712
+Epoch [466], train_loss: 0.053038, val_loss: 0.061267, val_acc: 23.199705
+Epoch [467], train_loss: 0.053061, val_loss: 0.061237, val_acc: 23.236984
+Epoch [468], train_loss: 0.053127, val_loss: 0.061371, val_acc: 23.239336
+Epoch [469], train_loss: 0.053023, val_loss: 0.061225, val_acc: 23.174282
+Epoch [470], train_loss: 0.053042, val_loss: 0.061271, val_acc: 23.139036
+Epoch [471], train_loss: 0.052993, val_loss: 0.061265, val_acc: 23.179932
+Epoch [472], train_loss: 0.052978, val_loss: 0.061300, val_acc: 23.167246
+Epoch [473], train_loss: 0.053037, val_loss: 0.061365, val_acc: 23.194050
+Epoch [474], train_loss: 0.053025, val_loss: 0.061336, val_acc: 23.159458
+Epoch [475], train_loss: 0.052988, val_loss: 0.061354, val_acc: 23.031950
+Epoch [476], train_loss: 0.052998, val_loss: 0.061254, val_acc: 23.146049
+Epoch [477], train_loss: 0.052960, val_loss: 0.061296, val_acc: 23.142622
+Epoch [478], train_loss: 0.052979, val_loss: 0.061507, val_acc: 22.992659
+Epoch [479], train_loss: 0.052926, val_loss: 0.061208, val_acc: 23.248734
+Epoch [480], train_loss: 0.052927, val_loss: 0.061266, val_acc: 23.229752
+Epoch [481], train_loss: 0.052962, val_loss: 0.061298, val_acc: 23.105995
+Epoch [482], train_loss: 0.052917, val_loss: 0.061347, val_acc: 23.126987
+Epoch [483], train_loss: 0.052931, val_loss: 0.061363, val_acc: 23.111250
+Epoch [484], train_loss: 0.052907, val_loss: 0.061391, val_acc: 23.077534
+Epoch [485], train_loss: 0.052933, val_loss: 0.061267, val_acc: 23.176140
+Epoch [486], train_loss: 0.052916, val_loss: 0.061261, val_acc: 23.191032
+Epoch [487], train_loss: 0.052898, val_loss: 0.061339, val_acc: 23.199249
+Epoch [488], train_loss: 0.052881, val_loss: 0.061303, val_acc: 23.226713
+Epoch [489], train_loss: 0.052903, val_loss: 0.061314, val_acc: 23.119341
+Epoch [490], train_loss: 0.052894, val_loss: 0.061351, val_acc: 23.146034
+Epoch [491], train_loss: 0.052855, val_loss: 0.061314, val_acc: 23.082550
+Epoch [492], train_loss: 0.052826, val_loss: 0.061455, val_acc: 23.086500
+Epoch [493], train_loss: 0.052873, val_loss: 0.061234, val_acc: 23.240562
+Epoch [494], train_loss: 0.052801, val_loss: 0.061310, val_acc: 23.136999
+Epoch [495], train_loss: 0.052853, val_loss: 0.061265, val_acc: 23.244812
+Epoch [496], train_loss: 0.052780, val_loss: 0.061412, val_acc: 23.108850
+Epoch [497], train_loss: 0.052811, val_loss: 0.061482, val_acc: 23.054136
+Epoch [498], train_loss: 0.052752, val_loss: 0.061321, val_acc: 23.161833
+Epoch [499], train_loss: 0.052745, val_loss: 0.061645, val_acc: 22.998936
+python3 ./UNet_V11.py  6585.36s user 6269.03s system 99% cpu 3:34:51.95 total
diff --git a/UNet/Sim_logs/UNet_V9_1_25594464.log b/UNet/Sim_logs/UNet_V9_1_25594464.log
new file mode 100644
index 0000000000000000000000000000000000000000..b50dea018f87fada722291c5c2e522a8d1ad2eaf
--- /dev/null
+++ b/UNet/Sim_logs/UNet_V9_1_25594464.log
@@ -0,0 +1,222 @@
+(OK) Loading cuda 10.2.89
+(OK) Loading python 3.7.11
+(!!) The SciPy Stack is available: http://www.scipy.org/stackspec.html
+ Built with GCC compilers.
+9.1 with no pading
+Collecting torch==1.10.1
+  Using cached torch-1.10.1-cp37-cp37m-manylinux1_x86_64.whl (881.9 MB)
+Collecting typing-extensions
+  Using cached typing_extensions-4.1.1-py3-none-any.whl (26 kB)
+Installing collected packages: typing-extensions, torch
+  WARNING: The scripts convert-caffe2-to-onnx, convert-onnx-to-caffe2 and torchrun are installed in '/home/yk138599/.local/bin' which is not on PATH.
+  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
+Successfully installed torch-1.10.1 typing-extensions-4.1.1
+WARNING: You are using pip version 21.2.4; however, version 22.0.3 is available.
+You should consider upgrading via the '/usr/local_rwth/sw/python/3.7.11/x86_64/bin/python3.7 -m pip install --upgrade pip' command.
+number auf epochs: 200
+batchsize: 32
+learning rate: 1e-05
+kernel size is: 5
+no reflecting padding
+ seed is: 373686838
+Epoch [0], train_loss: 0.222098, val_loss: 0.249357, val_acc: 4.366699
+Epoch [1], train_loss: 0.211698, val_loss: 0.205261, val_acc: 6.099843
+Epoch [2], train_loss: 0.204315, val_loss: 0.200491, val_acc: 6.370419
+Epoch [3], train_loss: 0.198532, val_loss: 0.195153, val_acc: 6.571845
+Epoch [4], train_loss: 0.193635, val_loss: 0.191961, val_acc: 6.710374
+Epoch [5], train_loss: 0.188720, val_loss: 0.186252, val_acc: 7.009617
+Epoch [6], train_loss: 0.183733, val_loss: 0.180922, val_acc: 7.366269
+Epoch [7], train_loss: 0.178640, val_loss: 0.176224, val_acc: 7.795247
+Epoch [8], train_loss: 0.173697, val_loss: 0.172467, val_acc: 8.238951
+Epoch [9], train_loss: 0.168918, val_loss: 0.166632, val_acc: 8.900542
+Epoch [10], train_loss: 0.164120, val_loss: 0.162864, val_acc: 9.528979
+Epoch [11], train_loss: 0.159670, val_loss: 0.159182, val_acc: 10.078839
+Epoch [12], train_loss: 0.155805, val_loss: 0.156144, val_acc: 10.543340
+Epoch [13], train_loss: 0.152454, val_loss: 0.153265, val_acc: 10.955722
+Epoch [14], train_loss: 0.149510, val_loss: 0.149041, val_acc: 11.436620
+Epoch [15], train_loss: 0.146918, val_loss: 0.145994, val_acc: 11.824395
+Epoch [16], train_loss: 0.144558, val_loss: 0.143601, val_acc: 12.230663
+Epoch [17], train_loss: 0.142398, val_loss: 0.142112, val_acc: 12.485040
+Epoch [18], train_loss: 0.140427, val_loss: 0.140545, val_acc: 12.776359
+Epoch [19], train_loss: 0.138498, val_loss: 0.138625, val_acc: 13.072968
+Epoch [20], train_loss: 0.136590, val_loss: 0.136001, val_acc: 13.390886
+Epoch [21], train_loss: 0.134942, val_loss: 0.136554, val_acc: 13.404213
+Epoch [22], train_loss: 0.133426, val_loss: 0.134724, val_acc: 13.687212
+Epoch [23], train_loss: 0.131981, val_loss: 0.131772, val_acc: 14.000846
+Epoch [24], train_loss: 0.130629, val_loss: 0.131407, val_acc: 14.169135
+Epoch [25], train_loss: 0.129334, val_loss: 0.130112, val_acc: 14.368894
+Epoch [26], train_loss: 0.128126, val_loss: 0.127828, val_acc: 14.542864
+Epoch [27], train_loss: 0.126930, val_loss: 0.127907, val_acc: 14.645527
+Epoch [28], train_loss: 0.125806, val_loss: 0.126024, val_acc: 14.932583
+Epoch [29], train_loss: 0.124720, val_loss: 0.124627, val_acc: 15.040679
+Epoch [30], train_loss: 0.123659, val_loss: 0.123916, val_acc: 15.081257
+Epoch [31], train_loss: 0.122576, val_loss: 0.121720, val_acc: 15.464638
+Epoch [32], train_loss: 0.121553, val_loss: 0.122170, val_acc: 15.492606
+Epoch [33], train_loss: 0.120578, val_loss: 0.120126, val_acc: 15.767668
+Epoch [34], train_loss: 0.119597, val_loss: 0.120290, val_acc: 15.748919
+Epoch [35], train_loss: 0.118686, val_loss: 0.119534, val_acc: 15.848437
+Epoch [36], train_loss: 0.117706, val_loss: 0.118068, val_acc: 16.003078
+Epoch [37], train_loss: 0.116777, val_loss: 0.117256, val_acc: 16.207539
+Epoch [38], train_loss: 0.115819, val_loss: 0.116925, val_acc: 16.186275
+Epoch [39], train_loss: 0.114971, val_loss: 0.114818, val_acc: 16.539066
+Epoch [40], train_loss: 0.114047, val_loss: 0.114886, val_acc: 16.669210
+Epoch [41], train_loss: 0.113181, val_loss: 0.113409, val_acc: 16.878906
+Epoch [42], train_loss: 0.112240, val_loss: 0.113480, val_acc: 16.825527
+Epoch [43], train_loss: 0.111404, val_loss: 0.110324, val_acc: 17.112352
+Epoch [44], train_loss: 0.110449, val_loss: 0.109505, val_acc: 17.302979
+Epoch [45], train_loss: 0.109414, val_loss: 0.109419, val_acc: 17.424042
+Epoch [46], train_loss: 0.108508, val_loss: 0.108674, val_acc: 17.548838
+Epoch [47], train_loss: 0.107619, val_loss: 0.105090, val_acc: 17.983927
+Epoch [48], train_loss: 0.106767, val_loss: 0.107005, val_acc: 17.769365
+Epoch [49], train_loss: 0.105934, val_loss: 0.106226, val_acc: 17.934483
+Epoch [50], train_loss: 0.105059, val_loss: 0.104916, val_acc: 17.991543
+Epoch [51], train_loss: 0.104157, val_loss: 0.105405, val_acc: 18.153887
+Epoch [52], train_loss: 0.103318, val_loss: 0.104017, val_acc: 18.309713
+Epoch [53], train_loss: 0.102474, val_loss: 0.102395, val_acc: 18.414904
+Epoch [54], train_loss: 0.101529, val_loss: 0.101862, val_acc: 18.623074
+Epoch [55], train_loss: 0.100663, val_loss: 0.101646, val_acc: 18.509089
+Epoch [56], train_loss: 0.099883, val_loss: 0.100914, val_acc: 18.779215
+Epoch [57], train_loss: 0.099193, val_loss: 0.098833, val_acc: 18.973827
+Epoch [58], train_loss: 0.098461, val_loss: 0.099157, val_acc: 19.160557
+Epoch [59], train_loss: 0.097791, val_loss: 0.099455, val_acc: 19.148010
+Epoch [60], train_loss: 0.097081, val_loss: 0.097686, val_acc: 19.395945
+Epoch [61], train_loss: 0.096421, val_loss: 0.095811, val_acc: 19.418203
+Epoch [62], train_loss: 0.095823, val_loss: 0.096089, val_acc: 19.503233
+Epoch [63], train_loss: 0.095192, val_loss: 0.095510, val_acc: 19.569139
+Epoch [64], train_loss: 0.094556, val_loss: 0.097077, val_acc: 19.428135
+Epoch [65], train_loss: 0.094001, val_loss: 0.095693, val_acc: 19.747505
+Epoch [66], train_loss: 0.093397, val_loss: 0.094685, val_acc: 19.879398
+Epoch [67], train_loss: 0.092867, val_loss: 0.095585, val_acc: 19.847897
+Epoch [68], train_loss: 0.092294, val_loss: 0.093428, val_acc: 20.163523
+Epoch [69], train_loss: 0.091680, val_loss: 0.094157, val_acc: 19.923470
+Epoch [70], train_loss: 0.091190, val_loss: 0.094148, val_acc: 20.083723
+Epoch [71], train_loss: 0.090648, val_loss: 0.091781, val_acc: 20.269018
+Epoch [72], train_loss: 0.090152, val_loss: 0.091112, val_acc: 20.530281
+Epoch [73], train_loss: 0.089549, val_loss: 0.091144, val_acc: 20.426090
+Epoch [74], train_loss: 0.089144, val_loss: 0.089014, val_acc: 20.811590
+Epoch [75], train_loss: 0.088680, val_loss: 0.090457, val_acc: 20.501333
+Epoch [76], train_loss: 0.088151, val_loss: 0.089131, val_acc: 20.669125
+Epoch [77], train_loss: 0.087681, val_loss: 0.091243, val_acc: 20.714216
+Epoch [78], train_loss: 0.087240, val_loss: 0.088279, val_acc: 20.802454
+Epoch [79], train_loss: 0.086956, val_loss: 0.085752, val_acc: 21.118738
+Epoch [80], train_loss: 0.086394, val_loss: 0.086553, val_acc: 21.015818
+Epoch [81], train_loss: 0.085983, val_loss: 0.086547, val_acc: 20.959036
+Epoch [82], train_loss: 0.085492, val_loss: 0.086791, val_acc: 21.124729
+Epoch [83], train_loss: 0.085093, val_loss: 0.085379, val_acc: 21.199276
+Epoch [84], train_loss: 0.084716, val_loss: 0.086202, val_acc: 21.045767
+Epoch [85], train_loss: 0.084356, val_loss: 0.085969, val_acc: 21.316843
+Epoch [86], train_loss: 0.084008, val_loss: 0.085442, val_acc: 21.237555
+Epoch [87], train_loss: 0.083452, val_loss: 0.083422, val_acc: 21.612595
+Epoch [88], train_loss: 0.083228, val_loss: 0.083847, val_acc: 21.577566
+Epoch [89], train_loss: 0.082841, val_loss: 0.086137, val_acc: 21.292143
+Epoch [90], train_loss: 0.082494, val_loss: 0.082061, val_acc: 21.746052
+Epoch [91], train_loss: 0.082111, val_loss: 0.084026, val_acc: 21.529114
+Epoch [92], train_loss: 0.081669, val_loss: 0.081587, val_acc: 21.897800
+Epoch [93], train_loss: 0.081380, val_loss: 0.084889, val_acc: 21.532196
+Epoch [94], train_loss: 0.081058, val_loss: 0.082855, val_acc: 21.717194
+Epoch [95], train_loss: 0.080655, val_loss: 0.080496, val_acc: 22.050018
+Epoch [96], train_loss: 0.080453, val_loss: 0.079909, val_acc: 22.180948
+Epoch [97], train_loss: 0.080090, val_loss: 0.080474, val_acc: 22.076614
+Epoch [98], train_loss: 0.079724, val_loss: 0.081813, val_acc: 21.952164
+Epoch [99], train_loss: 0.079475, val_loss: 0.080109, val_acc: 22.090036
+Epoch [100], train_loss: 0.079122, val_loss: 0.079036, val_acc: 22.184435
+Epoch [101], train_loss: 0.078764, val_loss: 0.079304, val_acc: 22.278584
+Epoch [102], train_loss: 0.078615, val_loss: 0.080055, val_acc: 22.240332
+Epoch [103], train_loss: 0.078339, val_loss: 0.077972, val_acc: 22.377216
+Epoch [104], train_loss: 0.078042, val_loss: 0.077437, val_acc: 22.450031
+Epoch [105], train_loss: 0.077724, val_loss: 0.077928, val_acc: 22.413092
+Epoch [106], train_loss: 0.077379, val_loss: 0.077269, val_acc: 22.479237
+Epoch [107], train_loss: 0.077122, val_loss: 0.078397, val_acc: 22.394133
+Epoch [108], train_loss: 0.076870, val_loss: 0.076435, val_acc: 22.595921
+Epoch [109], train_loss: 0.076563, val_loss: 0.076838, val_acc: 22.605242
+Epoch [110], train_loss: 0.076315, val_loss: 0.079340, val_acc: 22.401222
+Epoch [111], train_loss: 0.076073, val_loss: 0.075861, val_acc: 22.613630
+Epoch [112], train_loss: 0.075867, val_loss: 0.078635, val_acc: 22.528986
+Epoch [113], train_loss: 0.075597, val_loss: 0.076133, val_acc: 22.619078
+Epoch [114], train_loss: 0.075390, val_loss: 0.073380, val_acc: 22.928892
+Epoch [115], train_loss: 0.075118, val_loss: 0.076321, val_acc: 22.712927
+Epoch [116], train_loss: 0.074772, val_loss: 0.075789, val_acc: 22.696547
+Epoch [117], train_loss: 0.074641, val_loss: 0.074972, val_acc: 22.845533
+Epoch [118], train_loss: 0.074351, val_loss: 0.074792, val_acc: 22.880766
+Epoch [119], train_loss: 0.074132, val_loss: 0.073522, val_acc: 22.976292
+Epoch [120], train_loss: 0.073935, val_loss: 0.074684, val_acc: 22.958506
+Epoch [121], train_loss: 0.073852, val_loss: 0.073996, val_acc: 22.954554
+Epoch [122], train_loss: 0.073477, val_loss: 0.074788, val_acc: 22.918423
+Epoch [123], train_loss: 0.073172, val_loss: 0.073618, val_acc: 22.975239
+Epoch [124], train_loss: 0.073063, val_loss: 0.071950, val_acc: 23.141443
+Epoch [125], train_loss: 0.072872, val_loss: 0.072333, val_acc: 23.150114
+Epoch [126], train_loss: 0.072600, val_loss: 0.072723, val_acc: 23.250427
+Epoch [127], train_loss: 0.072376, val_loss: 0.072062, val_acc: 23.303749
+Epoch [128], train_loss: 0.072199, val_loss: 0.074129, val_acc: 23.042336
+Epoch [129], train_loss: 0.071997, val_loss: 0.072258, val_acc: 23.295826
+Epoch [130], train_loss: 0.071734, val_loss: 0.071272, val_acc: 23.325294
+Epoch [131], train_loss: 0.071514, val_loss: 0.071382, val_acc: 23.288467
+Epoch [132], train_loss: 0.071419, val_loss: 0.071099, val_acc: 23.380075
+Epoch [133], train_loss: 0.071210, val_loss: 0.070899, val_acc: 23.401894
+Epoch [134], train_loss: 0.071103, val_loss: 0.070430, val_acc: 23.356092
+Epoch [135], train_loss: 0.070777, val_loss: 0.071178, val_acc: 23.339596
+Epoch [136], train_loss: 0.070720, val_loss: 0.071425, val_acc: 23.320757
+Epoch [137], train_loss: 0.070493, val_loss: 0.071528, val_acc: 23.305351
+Epoch [138], train_loss: 0.070322, val_loss: 0.069032, val_acc: 23.558609
+Epoch [139], train_loss: 0.070065, val_loss: 0.068751, val_acc: 23.614559
+Epoch [140], train_loss: 0.069804, val_loss: 0.069682, val_acc: 23.527992
+Epoch [141], train_loss: 0.069749, val_loss: 0.069637, val_acc: 23.567375
+Epoch [142], train_loss: 0.069548, val_loss: 0.068954, val_acc: 23.681374
+Epoch [143], train_loss: 0.069370, val_loss: 0.067966, val_acc: 23.715033
+Epoch [144], train_loss: 0.069241, val_loss: 0.068430, val_acc: 23.669077
+Epoch [145], train_loss: 0.069069, val_loss: 0.069240, val_acc: 23.629400
+Epoch [146], train_loss: 0.068931, val_loss: 0.069268, val_acc: 23.613911
+Epoch [147], train_loss: 0.068699, val_loss: 0.069482, val_acc: 23.650122
+Epoch [148], train_loss: 0.068565, val_loss: 0.067995, val_acc: 23.766510
+Epoch [149], train_loss: 0.068446, val_loss: 0.068749, val_acc: 23.699957
+Epoch [150], train_loss: 0.068325, val_loss: 0.067583, val_acc: 23.830765
+Epoch [151], train_loss: 0.068112, val_loss: 0.067903, val_acc: 23.806755
+Epoch [152], train_loss: 0.067887, val_loss: 0.067680, val_acc: 23.807020
+Epoch [153], train_loss: 0.067792, val_loss: 0.067821, val_acc: 23.794025
+Epoch [154], train_loss: 0.067627, val_loss: 0.067337, val_acc: 23.875694
+Epoch [155], train_loss: 0.067522, val_loss: 0.065373, val_acc: 24.066999
+Epoch [156], train_loss: 0.067299, val_loss: 0.066895, val_acc: 23.880589
+Epoch [157], train_loss: 0.067216, val_loss: 0.066907, val_acc: 23.923481
+Epoch [158], train_loss: 0.067097, val_loss: 0.065912, val_acc: 24.040472
+Epoch [159], train_loss: 0.066913, val_loss: 0.066830, val_acc: 23.922209
+Epoch [160], train_loss: 0.066662, val_loss: 0.066746, val_acc: 23.962971
+Epoch [161], train_loss: 0.066762, val_loss: 0.066434, val_acc: 23.976194
+Epoch [162], train_loss: 0.066486, val_loss: 0.067469, val_acc: 23.910370
+Epoch [163], train_loss: 0.066349, val_loss: 0.066101, val_acc: 24.018082
+Epoch [164], train_loss: 0.066172, val_loss: 0.066191, val_acc: 23.989172
+Epoch [165], train_loss: 0.066216, val_loss: 0.067073, val_acc: 23.929794
+Epoch [166], train_loss: 0.065970, val_loss: 0.065154, val_acc: 24.112928
+Epoch [167], train_loss: 0.065904, val_loss: 0.066243, val_acc: 24.020464
+Epoch [168], train_loss: 0.065730, val_loss: 0.066742, val_acc: 24.001709
+Epoch [169], train_loss: 0.065520, val_loss: 0.065451, val_acc: 24.100451
+Epoch [170], train_loss: 0.065500, val_loss: 0.065927, val_acc: 24.075636
+Epoch [171], train_loss: 0.065418, val_loss: 0.063866, val_acc: 24.197458
+Epoch [172], train_loss: 0.065254, val_loss: 0.065421, val_acc: 24.092909
+Epoch [173], train_loss: 0.065111, val_loss: 0.065382, val_acc: 24.119747
+Epoch [174], train_loss: 0.064965, val_loss: 0.064884, val_acc: 24.211637
+Epoch [175], train_loss: 0.064920, val_loss: 0.064585, val_acc: 24.203943
+Epoch [176], train_loss: 0.064718, val_loss: 0.064597, val_acc: 24.224186
+Epoch [177], train_loss: 0.064633, val_loss: 0.063876, val_acc: 24.279900
+Epoch [178], train_loss: 0.064498, val_loss: 0.064524, val_acc: 24.201567
+Epoch [179], train_loss: 0.064404, val_loss: 0.063628, val_acc: 24.278339
+Epoch [180], train_loss: 0.064243, val_loss: 0.064257, val_acc: 24.252720
+Epoch [181], train_loss: 0.064196, val_loss: 0.065377, val_acc: 24.175459
+Epoch [182], train_loss: 0.064049, val_loss: 0.063184, val_acc: 24.315140
+Epoch [183], train_loss: 0.063922, val_loss: 0.064160, val_acc: 24.289366
+Epoch [184], train_loss: 0.063971, val_loss: 0.063787, val_acc: 24.300077
+Epoch [185], train_loss: 0.063811, val_loss: 0.063663, val_acc: 24.283232
+Epoch [186], train_loss: 0.063619, val_loss: 0.063983, val_acc: 24.289181
+Epoch [187], train_loss: 0.063550, val_loss: 0.063518, val_acc: 24.320250
+Epoch [188], train_loss: 0.063538, val_loss: 0.063514, val_acc: 24.291626
+Epoch [189], train_loss: 0.063404, val_loss: 0.062313, val_acc: 24.395512
+Epoch [190], train_loss: 0.063201, val_loss: 0.063702, val_acc: 24.291012
+Epoch [191], train_loss: 0.063165, val_loss: 0.063887, val_acc: 24.273569
+Epoch [192], train_loss: 0.063074, val_loss: 0.063468, val_acc: 24.364014
+Epoch [193], train_loss: 0.062979, val_loss: 0.063244, val_acc: 24.362602
+Epoch [194], train_loss: 0.062902, val_loss: 0.063047, val_acc: 24.394043
+Epoch [195], train_loss: 0.062794, val_loss: 0.063785, val_acc: 24.350794
+Epoch [196], train_loss: 0.062643, val_loss: 0.062785, val_acc: 24.430412
+Epoch [197], train_loss: 0.062585, val_loss: 0.062173, val_acc: 24.459150
+Epoch [198], train_loss: 0.062501, val_loss: 0.062688, val_acc: 24.440397
+Epoch [199], train_loss: 0.062377, val_loss: 0.061589, val_acc: 24.511108
+python3 ./UNet_V9_1_nopadding.py  2528.92s user 2432.12s system 99% cpu 1:22:58.59 total
diff --git a/UNet/Sim_logs/UNet_V9_1_25611080.log b/UNet/Sim_logs/UNet_V9_1_25611080.log
new file mode 100644
index 0000000000000000000000000000000000000000..0bc401d89ac2e7761fead0617ffac115edc92959
--- /dev/null
+++ b/UNet/Sim_logs/UNet_V9_1_25611080.log
@@ -0,0 +1,17 @@
+(OK) Loading cuda 10.2.89
+(OK) Loading python 3.7.11
+(!!) The SciPy Stack is available: http://www.scipy.org/stackspec.html
+ Built with GCC compilers.
+9.1 k=7 lr=1e-06
+Collecting torch==1.10.1
+  Using cached torch-1.10.1-cp37-cp37m-manylinux1_x86_64.whl (881.9 MB)
+Collecting typing-extensions
+  Using cached typing_extensions-4.1.1-py3-none-any.whl (26 kB)
+Installing collected packages: typing-extensions, torch
+  WARNING: The scripts convert-caffe2-to-onnx, convert-onnx-to-caffe2 and torchrun are installed in '/home/yk138599/.local/bin' which is not on PATH.
+  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
+Successfully installed torch-1.10.1 typing-extensions-4.1.1
+WARNING: You are using pip version 21.2.4; however, version 22.0.3 is available.
+You should consider upgrading via the '/usr/local_rwth/sw/python/3.7.11/x86_64/bin/python3.7 -m pip install --upgrade pip' command.
+python3: can't open file './UNet_V9_1py': [Errno 2] No such file or directory
+python3 ./UNet_V9_1py  0.02s user 0.00s system 43% cpu 0.052 total
diff --git a/UNet/Sim_logs/UNet_V9_1_25611141.log b/UNet/Sim_logs/UNet_V9_1_25611141.log
new file mode 100644
index 0000000000000000000000000000000000000000..275764a54bf4d79ac276ab894a95cf9b0318604d
--- /dev/null
+++ b/UNet/Sim_logs/UNet_V9_1_25611141.log
@@ -0,0 +1,52 @@
+(OK) Loading cuda 10.2.89
+(OK) Loading python 3.7.11
+(!!) The SciPy Stack is available: http://www.scipy.org/stackspec.html
+ Built with GCC compilers.
+9.1 k=7 lr=1e-06
+Collecting torch==1.10.1
+  Using cached torch-1.10.1-cp37-cp37m-manylinux1_x86_64.whl (881.9 MB)
+Collecting typing-extensions
+  Using cached typing_extensions-4.1.1-py3-none-any.whl (26 kB)
+Installing collected packages: typing-extensions, torch
+  WARNING: The scripts convert-caffe2-to-onnx, convert-onnx-to-caffe2 and torchrun are installed in '/home/yk138599/.local/bin' which is not on PATH.
+  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
+Successfully installed torch-1.10.1 typing-extensions-4.1.1
+WARNING: You are using pip version 21.2.4; however, version 22.0.3 is available.
+You should consider upgrading via the '/usr/local_rwth/sw/python/3.7.11/x86_64/bin/python3.7 -m pip install --upgrade pip' command.
+number auf epochs: 1000
+batchsize: 32
+learning rate: 1e-06
+kernel size is: 7
+ seed is: 373686838
+Epoch [0], train_loss: 0.206706, val_loss: 0.181629, val_acc: 4.916494
+Epoch [1], train_loss: 0.205707, val_loss: 0.201508, val_acc: 5.658985
+Epoch [2], train_loss: 0.204720, val_loss: 0.203679, val_acc: 5.675884
+Epoch [3], train_loss: 0.203796, val_loss: 0.203070, val_acc: 5.704246
+Epoch [4], train_loss: 0.202948, val_loss: 0.202405, val_acc: 5.728241
+Epoch [5], train_loss: 0.202103, val_loss: 0.201344, val_acc: 5.758857
+Epoch [6], train_loss: 0.201291, val_loss: 0.200838, val_acc: 5.784995
+Epoch [7], train_loss: 0.200538, val_loss: 0.199535, val_acc: 5.820594
+Epoch [8], train_loss: 0.199770, val_loss: 0.199398, val_acc: 5.837022
+Epoch [9], train_loss: 0.199036, val_loss: 0.198499, val_acc: 5.871386
+Epoch [10], train_loss: 0.198354, val_loss: 0.198015, val_acc: 5.899837
+Epoch [11], train_loss: 0.197691, val_loss: 0.197421, val_acc: 5.919308
+Epoch [12], train_loss: 0.197028, val_loss: 0.196440, val_acc: 5.958292
+Epoch [13], train_loss: 0.196418, val_loss: 0.196635, val_acc: 5.942986
+Epoch [14], train_loss: 0.195843, val_loss: 0.196651, val_acc: 5.943994
+Epoch [15], train_loss: 0.195247, val_loss: 0.195506, val_acc: 5.996199
+Epoch [16], train_loss: 0.194702, val_loss: 0.195039, val_acc: 6.016672
+Epoch [17], train_loss: 0.194129, val_loss: 0.194636, val_acc: 6.033465
+Epoch [18], train_loss: 0.193560, val_loss: 0.193872, val_acc: 6.070275
+Epoch [19], train_loss: 0.193066, val_loss: 0.194132, val_acc: 6.056251
+Epoch [20], train_loss: 0.192499, val_loss: 0.192775, val_acc: 6.105118
+Epoch [21], train_loss: 0.191946, val_loss: 0.191576, val_acc: 6.149546
+Epoch [22], train_loss: 0.191431, val_loss: 0.192843, val_acc: 6.100420
+Epoch [23], train_loss: 0.190886, val_loss: 0.191038, val_acc: 6.184750
+Epoch [24], train_loss: 0.190337, val_loss: 0.190717, val_acc: 6.190635
+Epoch [25], train_loss: 0.189784, val_loss: 0.189964, val_acc: 6.208762
+Epoch [26], train_loss: 0.189182, val_loss: 0.189992, val_acc: 6.208062
+Epoch [27], train_loss: 0.188621, val_loss: 0.188663, val_acc: 6.289221
+Epoch [28], train_loss: 0.188027, val_loss: 0.189067, val_acc: 6.282068
+Epoch [29], train_loss: 0.187412, val_loss: 0.188952, val_acc: 6.267137
+Epoch [30], train_loss: 0.186806, val_loss: 0.188327, val_acc: 6.304575
+Epoch [31], train_loss: 0.186197, val_loss: 0.187869, val_acc: 6.352044
diff --git a/UNet/UNet_V10.py b/UNet/UNet_V10.py
index 9f16b123be0a8f93a75178dc61d0d23273a6dbfa..ed8320cc84c52d9d3eba9e067282eb266e71a0ad 100644
--- a/UNet/UNet_V10.py
+++ b/UNet/UNet_V10.py
@@ -112,7 +112,7 @@ class UNetBase(nn.Module):
         input, labels = batch 
         out = self(input)                    # Generate predictions
         loss = F.l1_loss(out, labels)   # Calculate loss
-        acc = accuracy(out.detach(), labels.detach())         # Calculate accuracy
+        acc = accuracy(out.detach(), labels.detach(),normalization=self.normalization)         # Calculate accuracy
         return {'val_loss': loss.detach(), 'val_acc': acc}
         
     def validation_epoch_end(self, outputs):
diff --git a/UNet/UNet_V11.py b/UNet/UNet_V11.py
index f39a3fd060e3f347f4c0a99cc004cfe96e97c75e..20bcbb73d7d9fdf12deca7ee88f7d1046bc69ec8 100644
--- a/UNet/UNet_V11.py
+++ b/UNet/UNet_V11.py
@@ -1,4 +1,4 @@
-#like V6_2 but only the different phases as input
+
 """UNet_V6.ipynb
 
 Automatically generated by Colaboratory.
diff --git a/UNet/UNet_V9_1.py b/UNet/UNet_V9_1.py
index 9d0a6421475873e2e5eee12ced18dd07b79bc22e..675b6d135852edcde26d9fac56b93ffe1661720a 100644
--- a/UNet/UNet_V9_1.py
+++ b/UNet/UNet_V9_1.py
@@ -228,11 +228,11 @@ if __name__ == '__main__':
     path_to_rep = '/home/yk138599/Hiwi/damask3'
     use_seeds = True
     seed = 373686838
-    num_epochs = 500
+    num_epochs = 1000
     b_size = 32
     opt_func = torch.optim.Adam
-    lr = 0.00001
-    kernel = 5
+    lr = 0.000001
+    kernel = 7
     print(f'number auf epochs: {num_epochs}')
     print(f'batchsize: {b_size}')
     print(f'learning rate: {lr}')
diff --git a/UNet/UNet_V9_1_nopadding.py b/UNet/UNet_V9_1_nopadding.py
new file mode 100644
index 0000000000000000000000000000000000000000..592aa4048169bb301ba798f3b35d1899443b0aae
--- /dev/null
+++ b/UNet/UNet_V9_1_nopadding.py
@@ -0,0 +1,254 @@
+#like V6_2 but only the different phases as input
+"""UNet_V6.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1yvtk3lFo_x0ZiqtFdnR8jgcjPKy3nZA4
+"""
+
+import torch
+import torch.nn as nn
+import numpy as np
+import random
+from torch.utils.data.sampler import SubsetRandomSampler
+from torch.utils.data.dataloader import DataLoader
+from torch.utils.data import TensorDataset
+import torch.nn.functional as F
+from torch.utils.data import random_split
+from torch.nn.modules.activation import ReLU
+
+class depthwise_separable_conv(nn.Module):
+    def __init__(self, in_c, out_1_c, out_2_c, padding, kernel_size):
+        super(depthwise_separable_conv, self).__init__()
+        self.depthwise_1 = nn.Conv3d(in_c, in_c, kernel_size= kernel_size, padding=padding[0], groups=in_c, bias=True)
+        self.pointwise_1 = nn.Conv3d(in_c, out_1_c, kernel_size=1, bias=True)
+        self.batch_norm_1 = nn.BatchNorm3d(out_1_c)
+        self.relu = nn.ReLU()
+        self.depthwise_2 = nn.Conv3d(out_1_c, out_1_c, kernel_size= kernel_size, padding=padding[1], groups=out_1_c, bias=True)
+        self.pointwise_2 = nn.Conv3d(out_1_c, out_2_c, kernel_size=1, bias=True)
+        self.batch_norm_2 = nn.BatchNorm3d(out_2_c)
+    def forward(self, x):
+        x = self.batch_norm_1(self.relu(self.pointwise_1(self.depthwise_1(x))))
+        return self.batch_norm_2(self.relu(self.pointwise_2(self.depthwise_2(x))))
+
+class convolution_Layer(nn.Module):
+    def __init__(self, in_c, out_1_c, out_2_c, padding, kernel_size):
+        super(convolution_Layer, self).__init__()
+        self.conv_1 = nn.Conv3d(in_c, out_1_c, kernel_size= kernel_size, padding=padding[0], bias=True)
+        self.batch_norm_1 = nn.BatchNorm3d(out_1_c)
+        self.relu = nn.ReLU()
+        self.conv_2 = nn.Conv3d(out_1_c, out_2_c, kernel_size= kernel_size, padding=padding[1], bias=True)
+        self.batch_norm_2 = nn.BatchNorm3d(out_2_c)
+    def forward(self, x):
+        x = self.batch_norm_1(self.relu(self.conv_1(x)))
+        return self.batch_norm_2(self.relu(self.relu(self.conv_2(x))))
+
+class head_layer(nn.Module):
+    def __init__(self, in_c, out_c = 1, padding = "same"):
+        super(head_layer, self).__init__()
+        self.conv =  nn.Conv3d(in_c, out_c, kernel_size=1, bias=True)
+        self.sig = nn.Sigmoid()
+    def forward(self, x):
+        return self.sig(self.conv(x)) #convolution
+        #return self.sig(self.pointwise(self.depthwise(x))) #convolution
+
+class Encoder(nn.Module):
+    def __init__(self,kernel_size, chs, padding=(("same","same"),("same","same"),("same","same"))):
+      super().__init__()
+      self.channels = chs
+      self.enc_blocks = nn.ModuleList([depthwise_separable_conv(chs[i][0], chs[i][1], chs[i][2], kernel_size=kernel_size, padding=padding[i]) for i in range(len(chs))])
+      self.pool       = nn.MaxPool3d(kernel_size=2, stride=2)
+      #self.batch_norm = nn.ModuleList([nn.BatchNorm3d( chs[i][2]) for i in range(len(chs))])
+      self.periodic_upsample = nn.ReflectionPad3d(int((kernel_size-1)/2))
+
+    
+    def forward(self, x):
+      ftrs = []
+      #x = self.periodic_upsample(x)
+      for i in range(len(self.channels)):
+        ftrs.append(x)
+        x =self.enc_blocks[i](x)
+        #print(f'size of ftrs: {ftrs[i].size()}')
+        x = self.pool(x)
+        #print(f'size of x after pooling{x.size()}')
+      ftrs.append(x)
+      #print(f'size of ftrs: {ftrs[3].size()}')
+      #print(f'length of ftrs: {len(ftrs)}')
+      return ftrs
+
+class Decoder(nn.Module):
+    def __init__(self,kernel_size, chs_upsampling, chs_conv, padding=(("same","same"),("same","same"),("same","same"))):
+        super().__init__()
+        assert len(chs_conv) == len(chs_upsampling)
+        self.chs         = chs_upsampling
+        self.upconvs    = nn.ModuleList([nn.ConvTranspose3d(chs_upsampling[i], chs_upsampling[i], 2, 2) for i in range(len(chs_upsampling))])
+        self.dec_blocks = nn.ModuleList([depthwise_separable_conv(chs_conv[i][0], chs_conv[i][1], chs_conv[i][2], kernel_size=kernel_size, padding=padding[i]) for i in range(len(chs_conv))])
+        self.head = head_layer(chs_conv[-1][2])
+    def forward(self, x, encoder_features):
+        for i in range(len(self.chs)):
+            x        = self.upconvs[i](x)
+            #print(f'size after upsampling: {x.size()}')
+            enc_ftrs = self.crop(encoder_features[i], x)
+            x        = torch.cat([x, enc_ftrs], dim=1)
+            #print(f'size after cropping&cat: {x.size()}')
+
+            x        = self.dec_blocks[i](x)
+            #print(f'size after convolution: {x.size()}')
+        x = self.head(x)    
+        return x
+    
+    def crop(self, tensor, target_tensor):
+        target_size = target_tensor.size()[2]
+        tensor_size = tensor.size()[2]
+        delta = tensor_size - target_size
+        delta = delta // 2
+        return tensor[:,:,delta:tensor_size-delta,delta:tensor_size-delta,delta:tensor_size-delta]
+
+class UNetBase(nn.Module):
+    def training_step(self, batch):
+        input, labels = batch 
+        out = self(input)                  # Generate predictions
+        loss = F.l1_loss(out, labels) # Calculate loss
+        return loss
+    
+    def validation_step(self, batch):
+        input, labels = batch 
+        out = self(input)                    # Generate predictions
+        loss = F.l1_loss(out, labels)   # Calculate loss
+        acc = accuracy(out.detach(), labels.detach(),normalization=self.normalization)         # Calculate accuracy
+        return {'val_loss': loss.detach(), 'val_acc': acc}
+        
+    def validation_epoch_end(self, outputs):
+        batch_losses = [x['val_loss'] for x in outputs]
+        epoch_loss = torch.stack(batch_losses).mean()   # Combine losses
+        batch_accs = [x['val_acc'] for x in outputs]
+        epoch_acc = torch.stack(batch_accs).mean()      # Combine accuracies
+        return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()}
+    
+    def epoch_end(self, epoch, result):
+        print("Epoch [{}], train_loss: {:.6f}, val_loss: {:.6f}, val_acc: {:.6f}".format(
+            epoch, result['train_loss'], result['val_loss'], result['val_acc']))
+        
+def accuracy(outputs, labels,normalization, threshold = 0.05):
+    error = (abs((outputs) - (labels)))/(outputs+normalization[0]/normalization[1])
+    right_predic = torch.sum(error < threshold)
+    percentage = ((right_predic/torch.numel(error))*100.)
+    return percentage
+    
+class UNet(UNetBase):
+    def __init__(self,kernel_size = 5, enc_chs=((2,16,32), (32,32,64), (64,64,128)), dec_chs_up=(128, 128, 64), dec_chs_conv=((192,128, 128),(160,64,64),(66,32,32)),normalization=np.array([0,1])):
+        super().__init__()
+        self.encoder     = Encoder(kernel_size = kernel_size, chs = enc_chs)
+        self.decoder     = Decoder(kernel_size = kernel_size, chs_upsampling = dec_chs_up, chs_conv = dec_chs_conv)
+        #self.head        = depthwise_separable_conv(1, 1, padding = "same", kernel_size=1)
+        self.normalization = normalization
+
+
+    def forward(self, x):
+        enc_ftrs = self.encoder(x)
+        out      = self.decoder(enc_ftrs[::-1][0], enc_ftrs[::-1][1:])
+        #out      = self.head(out)
+        return out
+
+@torch.no_grad()
+def evaluate(model, val_loader):
+    model.eval()
+    outputs = [model.validation_step(batch) for batch in val_loader]
+    return model.validation_epoch_end(outputs)
+
+def fit(epochs, lr, model, train_loader, val_loader, path, opt_func=torch.optim.Adam):
+    history = []
+    optimizer = opt_func(model.parameters(), lr, eps=1e-07)
+    for epoch in range(epochs):
+        # Training Phase 
+        model.train()
+        train_losses = []
+        for batch in train_loader:
+            loss = model.training_step(batch)
+            train_losses.append(loss)
+            loss.backward()
+            optimizer.step()
+            optimizer.zero_grad()
+        # Validation phase
+        result = evaluate(model, val_loader)
+        result['train_loss'] = torch.stack(train_losses).mean().item()
+        model.epoch_end(epoch, result)
+        history.append(result)
+    torch.save(model.state_dict(),f'{path}/Unet_dict_V9_1.pth')
+    torch.save(history,f'{path}/history_V9_1.pt')
+    return history
+
+def get_default_device():
+    """Pick GPU if available, else CPU"""
+    if torch.cuda.is_available():
+        return torch.device('cuda')
+    else:
+      print('no GPU found')
+      return torch.device('cpu')
+      
+def to_device(data, device):
+    """Move tensor(s) to chosen device"""
+    if isinstance(data, (list,tuple)):
+        return [to_device(x, device) for x in data]
+    return data.to(device, non_blocking=True)
+
+class DeviceDataLoader():
+    """Wrap a dataloader to move data to a device"""
+    def __init__(self, dl, device):
+        self.dl = dl
+        self.device = device
+        
+    def __iter__(self):
+        """Yield a batch of data after moving it to device"""
+        for b in self.dl: 
+            yield to_device(b, self.device)
+
+    def __len__(self):
+        """Number of batches"""
+        return len(self.dl)
+
+def Create_Dataloader(path, batch_size = 100, percent_val = 0.2):
+    dataset = torch.load(path) # create the pytorch dataset 
+    #size_data = 500 #shrink dataset for colab
+    #rest = len(dataset) -size_data
+    #dataset,_ = torch.utils.data.random_split(dataset, [size_data, rest])
+    val_size = int(len(dataset) * percent_val)
+    train_size = len(dataset) - val_size
+
+    train_ds, val_ds = random_split(dataset, [train_size, val_size])
+    # Create DataLoader
+    train_dl = DataLoader(train_ds, batch_size, shuffle=True, num_workers=1, pin_memory=True)
+    valid_dl = DataLoader(val_ds, batch_size, num_workers=1, pin_memory=True)
+    
+    return train_dl, valid_dl
+
+if __name__ == '__main__':
+    #os.chdir('F:/RWTH/HiWi_IEHK/DAMASK3/UNet/Trainingsdata')
+    path_to_rep = '/home/yk138599/Hiwi/damask3'
+    use_seeds = True
+    seed = 373686838
+    num_epochs = 200
+    b_size = 32
+    opt_func = torch.optim.Adam
+    lr = 0.00001
+    kernel = 5
+    print(f'number auf epochs: {num_epochs}')
+    print(f'batchsize: {b_size}')
+    print(f'learning rate: {lr}')
+    print(f'kernel size is: {kernel}')
+    print('no reflecting padding')
+    if not use_seeds:
+      seed = random.randrange(2**32 - 1)
+    print(f' seed is: {seed}')
+    torch.manual_seed(seed)
+    random.seed(seed)
+    np.random.seed(seed)
+    device = get_default_device()
+    normalization = np.load(f'{path_to_rep}/UNet/Trainingsdata/Norm_min_max_32_phase_only.npy', allow_pickle = True)
+    train_dl, valid_dl = Create_Dataloader(f'{path_to_rep}/UNet/Trainingsdata/TD_norm_32_phase_only.pt', batch_size= b_size )
+    train_dl = DeviceDataLoader(train_dl, device)
+    valid_dl = DeviceDataLoader(valid_dl, device)
+
+    model = to_device(UNet(kernel_size=kernel,normalization=normalization).double(), device)
+    history = fit(num_epochs, lr, model, train_dl, valid_dl,f'{path_to_rep}/UNet/output', opt_func)
diff --git a/UNet/UNet_V9_2.py b/UNet/UNet_V9_2.py
index 886846e464e23278dbde1bd5df84be223152bacd..f837a3632047a3e445d5874b531fdbf97153dcf7 100644
--- a/UNet/UNet_V9_2.py
+++ b/UNet/UNet_V9_2.py
@@ -231,7 +231,7 @@ if __name__ == '__main__':
     num_epochs = 500
     b_size = 32
     opt_func = torch.optim.Adam
-    lr = 0.00001
+    lr = 0.00003
     kernel = 7
     print(f'number auf epochs: {num_epochs}')
     print(f'batchsize: {b_size}')
diff --git a/UNet/UNet_V9_3.py b/UNet/UNet_V9_3.py
index 8453bc792f10eb753a017f1f514e110bc0a4d7e3..0c07f78b7f6f9fba88c465d079c53af0ec45360b 100644
--- a/UNet/UNet_V9_3.py
+++ b/UNet/UNet_V9_3.py
@@ -231,7 +231,7 @@ if __name__ == '__main__':
     num_epochs = 500
     b_size = 32
     opt_func = torch.optim.Adam
-    lr = 0.00001
+    lr = 0.00005
     kernel = 3
     print(f'number auf epochs: {num_epochs}')
     print(f'batchsize: {b_size}')