From ef4ef5823a6613a33d329cb1f2998bfa4cf51c9d Mon Sep 17 00:00:00 2001
From: Jannis Klinkenberg <j.klinkenberg@itc.rwth-aachen.de>
Date: Fri, 8 Nov 2024 18:19:28 +0100
Subject: [PATCH] small fixes

---
 pytorch/cifar10/submit_job_venv.sh                   |  2 +-
 pytorch/cifar10_distributed/submit_job_venv.sh       |  2 +-
 pytorch/mnist/submit_job_venv.sh                     |  2 +-
 pytorch/mnist_distributed/submit_job_venv.sh         |  2 +-
 tensorflow/cifar10/submit_job_container.sh           |  6 +++---
 tensorflow/cifar10/submit_job_venv.sh                | 12 +-----------
 .../cifar10_distributed/submit_job_container.sh      |  4 ++--
 tensorflow/cifar10_distributed/submit_job_venv.sh    | 12 +-----------
 8 files changed, 11 insertions(+), 31 deletions(-)

diff --git a/pytorch/cifar10/submit_job_venv.sh b/pytorch/cifar10/submit_job_venv.sh
index 982188f..ec783c5 100644
--- a/pytorch/cifar10/submit_job_venv.sh
+++ b/pytorch/cifar10/submit_job_venv.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
diff --git a/pytorch/cifar10_distributed/submit_job_venv.sh b/pytorch/cifar10_distributed/submit_job_venv.sh
index ff2fe92..38fde6e 100644
--- a/pytorch/cifar10_distributed/submit_job_venv.sh
+++ b/pytorch/cifar10_distributed/submit_job_venv.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
diff --git a/pytorch/mnist/submit_job_venv.sh b/pytorch/mnist/submit_job_venv.sh
index 982188f..ec783c5 100644
--- a/pytorch/mnist/submit_job_venv.sh
+++ b/pytorch/mnist/submit_job_venv.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
diff --git a/pytorch/mnist_distributed/submit_job_venv.sh b/pytorch/mnist_distributed/submit_job_venv.sh
index ff2fe92..38fde6e 100644
--- a/pytorch/mnist_distributed/submit_job_venv.sh
+++ b/pytorch/mnist_distributed/submit_job_venv.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
diff --git a/tensorflow/cifar10/submit_job_container.sh b/tensorflow/cifar10/submit_job_container.sh
index fa9b7b5..0e6f440 100644
--- a/tensorflow/cifar10/submit_job_container.sh
+++ b/tensorflow/cifar10/submit_job_container.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# load module for PyTorch container
+# load module for TensorFlow container
 module load TensorFlow/nvcr-24.01-tf2-py3
 module list
 
@@ -36,11 +36,11 @@ export NCCL_SOCKET_NTHREADS=8 # multi-threading for NCCL communication
 ### Execution (Model Training)
 ############################################################
 
-# tensorflow in container often needs a tmp directory
+# TensorFlow in container often needs a tmp directory
 NEWTMP=$(pwd)/tmp
 mkdir -p ${NEWTMP}
 
 # run the python script inside the container
 source set_vars.sh
 apptainer exec -e --nv -B ${NEWTMP}:/tmp ${TENSORFLOW_IMAGE} \
-    bash -c "python -W ignore train_model.py"'
+    bash -c "python -W ignore train_model.py"
diff --git a/tensorflow/cifar10/submit_job_venv.sh b/tensorflow/cifar10/submit_job_venv.sh
index cc27dd6..6a03c40 100644
--- a/tensorflow/cifar10/submit_job_venv.sh
+++ b/tensorflow/cifar10/submit_job_venv.sh
@@ -9,22 +9,12 @@
 #SBATCH --ntasks-per-node=2
 #SBATCH --cpus-per-task=24
 #SBATCH --gres=gpu:2
-#SBATCH --account=supp0001
 
 ############################################################
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
-module purge
-module load GCC/11.3.0
-module load OpenMPI/4.1.4
-module load CMake/3.21.1
-module load Python/3.9.6
-module load NCCL/2.20.5-CUDA-12.4.0
-module load cuDNN/8.9.7.29-CUDA-12.3.0
-
-source /work/jk869269/venvs/tensorflow-2.17_CUDA-12.3/bin/activate
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
diff --git a/tensorflow/cifar10_distributed/submit_job_container.sh b/tensorflow/cifar10_distributed/submit_job_container.sh
index 8fc8291..3e1a1e7 100644
--- a/tensorflow/cifar10_distributed/submit_job_container.sh
+++ b/tensorflow/cifar10_distributed/submit_job_container.sh
@@ -14,7 +14,7 @@
 ### Load modules or software
 ############################################################
 
-# load module for PyTorch container
+# load module for TensorFlow container
 module load TensorFlow/nvcr-24.01-tf2-py3
 module list
 
@@ -36,7 +36,7 @@ export NCCL_SOCKET_NTHREADS=8 # multi-threading for NCCL communication
 ### Execution (Model Training)
 ############################################################
 
-# tensorflow in container often needs a tmp directory
+# TensorFlow in container often needs a tmp directory
 NEWTMP=$(pwd)/tmp
 mkdir -p ${NEWTMP}
 
diff --git a/tensorflow/cifar10_distributed/submit_job_venv.sh b/tensorflow/cifar10_distributed/submit_job_venv.sh
index be3ff76..14e2209 100644
--- a/tensorflow/cifar10_distributed/submit_job_venv.sh
+++ b/tensorflow/cifar10_distributed/submit_job_venv.sh
@@ -9,22 +9,12 @@
 #SBATCH --ntasks-per-node=2
 #SBATCH --cpus-per-task=24
 #SBATCH --gres=gpu:2
-#SBATCH --account=supp0001
 
 ############################################################
 ### Load modules or software
 ############################################################
 
-# TODO: activate your desired virtual environment
-module purge
-module load GCC/11.3.0
-module load OpenMPI/4.1.4
-module load CMake/3.21.1
-module load Python/3.9.6
-module load NCCL/2.20.5-CUDA-12.4.0
-module load cuDNN/8.9.7.29-CUDA-12.3.0
-
-source /work/jk869269/venvs/tensorflow-2.17_CUDA-12.3/bin/activate
+# TODO: load/activate your desired modules and virtual environment
 
 ############################################################
 ### Parameters and Settings
-- 
GitLab