From b2222859b797be2597264a2f5fb8e49725555408 Mon Sep 17 00:00:00 2001
From: Xuan Gu <xuan.gu@liu.se>
Date: Fri, 24 Feb 2023 17:17:23 +0000
Subject: [PATCH] Update benchmark_multi_node.sbatch
---
scripts/benchmark_multi_node.sbatch | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/scripts/benchmark_multi_node.sbatch b/scripts/benchmark_multi_node.sbatch
index be6fd66..7971516 100644
--- a/scripts/benchmark_multi_node.sbatch
+++ b/scripts/benchmark_multi_node.sbatch
@@ -9,18 +9,18 @@
# For singularity
rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json
-srun singularity exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif python /workspace/nnunet_pyt/scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json"
+srun singularity exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json""
-rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json
-srun singularity exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif python /workspace/nnunet_pyt/scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json"
+#rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json
+#srun singularity exec --nv -B ${PWD}/data:/data -B ${PWD}/results:/results nvidia_nnu-net_for_pytorch.sif bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json""
############## Running srun enroot ... stopped working at 20220220
# For enroot
#rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json
-#srun enroot start --rw --mount ${PWD}/data:/data --mount ${PWD}/results:/results nnunet sh -c "python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json""
+#srun enroot start --rw --mount ${PWD}/data:/data --mount ${PWD}/results:/results nnunet bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json""
#rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json
-#srun enroot start --rw --mount ${PWD}/data:/data --mount ${PWD}/results:/results nnunet sh -c "python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json""
+#srun enroot start --rw --mount ${PWD}/data:/data --mount ${PWD}/results:/results nnunet bash -c "cd /workspace/nnunet_pyt && python scripts/benchmark.py --mode train --gpus ${3} --dim ${1} --batch_size ${4} --nodes ${2} --amp --logname="benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json""
############## Running srun with pyxis works
# For enroot
--
GitLab