Merge branch 'master' of git-ce.rwth-aachen.de:wasels.chr/damask3

merge cluster work

Merge branch 'master' of git-ce.rwth-aachen.de:wasels.chr/damask3
260058fc · Brian Christopher Wasels · 04af532c · c4e18fe5 · 260058fc · 260058fc
Commit 260058fc authored Feb 23, 2022 by Brian Christopher Wasels
--- a/Bericht/Bilder/UNet_Architecture.png
+++ b/Bericht/Bilder/UNet_Architecture.png
--- a/Bericht/Bilder/UNet_Architecture.svg
+++ b/Bericht/Bilder/UNet_Architecture.svg
--- a/Bericht/Bilder/UNet_MaxPlanck.png
+++ b/Bericht/Bilder/UNet_MaxPlanck.png
--- a/Notes.txt
+++ b/Notes.txt
--- a/UNet/NormalizeTrainingdata_64.ipynb
+++ b/UNet/NormalizeTrainingdata_64.ipynb
@@ -14,14 +14,12 @@
      "source": [
        "import torch\n",
        "import numpy as np\n",
-        "import torch.nn as nn\n",
-        "from torch.utils.data import TensorDataset\n",
-        "import sklearn.preprocessing as sp\n"
+        "from torch.utils.data import TensorDataset\n"
      ]
    },
    {
      "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
@@ -38,6 +36,8 @@
      "source": [
        "training_data = np.load('E:/Data/damask3/UNet/Input/Training_data_64.npy')\n",
        "training_label =  np.load('E:/Data/damask3/UNet/Input/Training_labels_64.npy')\n",
+        "training_data = training_data[0:50]\n",
+        "training_label = training_label[0:50]\n",
        "\n",
        "if training_data.shape[0] != training_label.shape[0]:\n",
        "    print('label and data have not the same size')\n",
@@ -48,7 +48,7 @@
    },
    {
      "cell_type": "code",
-      "execution_count": 6,
+      "execution_count": 7,
      "metadata": {
        "id": "lUnBE7T4q3Pi"
      },
@@ -72,7 +72,7 @@
    },
    {
      "cell_type": "code",
-      "execution_count": 7,
+      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
@@ -85,8 +85,8 @@
          "name": "stdout",
          "output_type": "stream",
          "text": [
-            "size of input is torch.Size([791, 6, 64, 64, 64])\n",
-            "size of label is torch.Size([791, 64, 64, 64])\n"
+            "size of input is torch.Size([50, 2, 64, 64, 64])\n",
+            "size of label is torch.Size([50, 64, 64, 64])\n"
          ]
        }
      ],
@@ -95,8 +95,9 @@
        "phase= data[:,4,:,:,:].reshape(data.shape[0], 1,64,64,64)\n",
        "new_phase = np.ones(phase.shape) - phase #input[4]: martinsite, input[5]:ferrit\n",
        "#new_training_data = np.append(data,new_channel,axis=1)\n",
-        "input = np.append(angles,phase,axis=1)\n",
-        "input = np.append(input,new_phase,axis=1)\n",
+        "#input = np.append(angles,phase,axis=1)\n",
+        "#input = np.append(input,new_phase,axis=1)\n",
+        "input = np.append(phase,new_phase,axis=1)\n",
        "\n",
        "label = torch.from_numpy(training_label)\n",
        "input = torch.from_numpy(input)\n",
@@ -112,7 +113,7 @@
    },
    {
      "cell_type": "code",
-      "execution_count": 8,
+      "execution_count": 4,
      "metadata": {
        "id": "Kgd1WhOODim3"
      },
@@ -130,15 +131,15 @@
    },
    {
      "cell_type": "code",
-      "execution_count": 9,
+      "execution_count": 5,
      "metadata": {
        "id": "-Rbt8Brb9mM_"
      },
      "outputs": [],
      "source": [
        "dataset = TensorDataset(input,label_normalized) # create the pytorch dataset \n",
-        "np.save('E:/Data/damask3/UNet/Input/Norm_min_max_64_angles.npy',[min_label, max_label])\n",
-        "torch.save(dataset,'E:/Data/damask3/UNet/Input/TD_norm_64_angles.pt')\n"
+        "np.save('E:/Data/damask3/UNet/Input/Norm_min_max_64_subset_phase.npy',[min_label, max_label])\n",
+        "torch.save(dataset,'E:/Data/damask3/UNet/Input/TD_norm_64_subset_phase.pt')\n"
      ]
    }
  ],

 %% Cell type:code id: tags:

 ``` python
 import torch
 import numpy as np
-import torch.nn as nn
 from torch.utils.data import TensorDataset
-import sklearn.preprocessing as sp
 ```

 %% Cell type:code id: tags:

 ``` python
 min_label, max_label,angles_min_max = np.load('E:/Data/damask3/UNet/Input/Norm_min_max_64.npy', allow_pickle= True)
 ```

 %% Cell type:code id: tags:

 ``` python
 training_data = np.load('E:/Data/damask3/UNet/Input/Training_data_64.npy')
 training_label =  np.load('E:/Data/damask3/UNet/Input/Training_labels_64.npy')
+training_data = training_data[0:50]
+training_label = training_label[0:50]

 if training_data.shape[0] != training_label.shape[0]:
    print('label and data have not the same size')
    #Desired input shape: (N,C,D,H,W) N=Batchsize, C=Channel, D=Depth, H=Height, W = Width
 data = np.moveaxis(training_data,4,1) # GAN output has shape(N,W,H,D,C) but no need to change spatial dimensions, but Channel dimension must be changed
 #input[0-3]: Orientation, input[4]: Phase(one for martinsite)
 ```

 %% Cell type:code id: tags:

 ``` python
 angles = data[:,0:4,...]
 angles_min_max= np.zeros((2,angles.shape[1]))

 for i in range(angles.shape[1]):
  s_batch,_,width, height, depth = angles.shape

  column= angles[:,i,...]
  angles_min_max[0,i] = column.min()
  angles_min_max[1,i] = column.max()
  column -= angles_min_max[0,i]
  column /=  angles_min_max[1,i]
  column = column.reshape(s_batch,width, height, depth)
  angles[:,i,...] = column

 ```

 %% Cell type:code id: tags:

 ``` python
 #training_label = training_label[:,np.newaxis,...]
 phase= data[:,4,:,:,:].reshape(data.shape[0], 1,64,64,64)
 new_phase = np.ones(phase.shape) - phase #input[4]: martinsite, input[5]:ferrit
 #new_training_data = np.append(data,new_channel,axis=1)
-input = np.append(angles,phase,axis=1)
-input = np.append(input,new_phase,axis=1)
+#input = np.append(angles,phase,axis=1)
+#input = np.append(input,new_phase,axis=1)
+input = np.append(phase,new_phase,axis=1)

 label = torch.from_numpy(training_label)
 input = torch.from_numpy(input)
 if label.dtype != torch.float64:
    label = label.double()
 if input.dtype != torch.float64:
    input = input.double()
 #angles = torch.from_numpy(angles)

 print(f'size of input is {input.size()}')
 print(f'size of label is {label.size()}')
 ```

 %% Output

-    size of input is torch.Size([791, 6, 64, 64, 64])
-    size of label is torch.Size([791, 64, 64, 64])
+    size of input is torch.Size([50, 2, 64, 64, 64])
+    size of label is torch.Size([50, 64, 64, 64])

 %% Cell type:code id: tags:

 ``` python
 label_normalized = label.view(label.size(0), -1)
 min_label = label_normalized.min().numpy()
 max_label = label_normalized.max().numpy()
 s_batch, width, height, depth = label.size()
 label_normalized -= min_label
 label_normalized /= max_label
 label_normalized = label_normalized.view(s_batch, width, height, depth)
 label_normalized = label_normalized[:,np.newaxis,...]
 ```

 %% Cell type:code id: tags:

 ``` python
 dataset = TensorDataset(input,label_normalized) # create the pytorch dataset
-np.save('E:/Data/damask3/UNet/Input/Norm_min_max_64_angles.npy',[min_label, max_label])
-torch.save(dataset,'E:/Data/damask3/UNet/Input/TD_norm_64_angles.pt')
+np.save('E:/Data/damask3/UNet/Input/Norm_min_max_64_subset_phase.npy',[min_label, max_label])
+torch.save(dataset,'E:/Data/damask3/UNet/Input/TD_norm_64_subset_phase.pt')
 ```

--- a/UNet/postprocessing_new.ipynb
+++ b/UNet/postprocessing_new.ipynb