diff --git a/PyTorch/Segmentation/nnUNet/benchmark.txt b/PyTorch/Segmentation/nnUNet/benchmark.txt index 55b265bb253878925c8c08036655658c7217d3ca..6cf9593895057f8cc139091c8ce5750d4a065e1d 100644 --- a/PyTorch/Segmentation/nnUNet/benchmark.txt +++ b/PyTorch/Segmentation/nnUNet/benchmark.txt @@ -8,20 +8,17 @@ CONTAINER_DIR=/proj/nsc_testing/xuan/containers/${MODULE_NAME}_${MODULE_VERSION} mkdir -p $WORK_DIR/data $WORK_DIR/results -export APPTAINER_BINDPATH=$WORK_DIR/data:/data,$WORK_DIR/results:/results - - To download and preprocess the data run: -apptainer exec --nv --pwd /workspace/nnunet_pyt $CONTAINER_DIR python download.py --task 01 +apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results --pwd /workspace/nnunet_pyt $CONTAINER_DIR python download.py --task 01 -apptainer exec --nv --pwd /workspace/nnunet_pyt $CONTAINER_DIR python /workspace/nnunet_pyt/preprocess.py --task 01 --dim 2 +apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results --pwd /workspace/nnunet_pyt $CONTAINER_DIR python /workspace/nnunet_pyt/preprocess.py --task 01 --dim 2 Start benchmarking: -apptainer exec --nv --pwd /workspace/nnunet_pyt $CONTAINER_DIR python scripts/benchmark.py --mode train --gpus 1 --dim 2 --batch_size 256 --amp +apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results --pwd /workspace/nnunet_pyt $CONTAINER_DIR python scripts/benchmark.py --mode train --gpus 1 --dim 2 --batch_size 256 --amp -apptainer exec --nv --pwd /workspace/nnunet_pyt $CONTAINER_DIR python scripts/benchmark.py --mode predict --gpus 1 --dim 2 --batch_size 256 --amp +apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results --pwd /workspace/nnunet_pyt $CONTAINER_DIR python scripts/benchmark.py --mode predict --gpus 1 --dim 2 --batch_size 256 --amp # Known issue https://github.com/NVIDIA/DeepLearningExamples/issues/1113 diff --git a/PyTorch/Segmentation/nnUNet/run_benchmark_single_node.sh b/PyTorch/Segmentation/nnUNet/run_benchmark_single_node.sh index cdd419cc438857ea238d30eaf45a106682d8131b..0c442f861dcda394d55001ccafb872a42bee919d 100644 --- a/PyTorch/Segmentation/nnUNet/run_benchmark_single_node.sh +++ b/PyTorch/Segmentation/nnUNet/run_benchmark_single_node.sh @@ -25,7 +25,7 @@ WORK_DIR=/proj/nsc_testing/xuan/berzelius-benchmarks/PyTorch/Segmentation/nnUNet CONTAINER_DIR=/proj/nsc_testing/xuan/containers/${MODULE_NAME}_${MODULE_VERSION}.sif rm -f $WORK_DIR/results/$LOG_DIR -apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results $CONTAINER_DIR bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname='$LOG_DIR'" +apptainer exec --nv -B ${WORK_DIR}/data:/data -B ${WORK_DIR}/results:/results --pwd /workspace/nnunet_pyt $CONTAINER_DIR python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname='$LOG_DIR' EOT