diff --git a/README.md b/README.md index afc9592a581c1f80c74aa35d0d16241e42d0472d..6c8d2bdb2131c9b2167eaff0da173bf74d392842 100644 --- a/README.md +++ b/README.md @@ -68,7 +68,7 @@ The input arguments are: We will average the benchmark performance over the iterations. The maximum usable (without a OOM error) batch size is 256 and 128 for single and multi-node, respectively. ``` cd cd Berzelius-nnU-Net-Benchmark && mkdir -p sbatch_out -bash scripts/benchmark_sbatch_submit.sh 2 1 8 10 128 +bash scripts/benchmark_sbatch_submit.sh 2 1 8 1 128 ``` ### Results diff --git a/scripts/benchmark_single_node.sbatch b/scripts/benchmark_single_node.sbatch index 30b90b6fa0e7f79ab09d068229042b3f55ba0189..a2d31397a206aa238c23bc4080908668e5c1284b 100644 --- a/scripts/benchmark_single_node.sbatch +++ b/scripts/benchmark_single_node.sbatch @@ -10,10 +10,10 @@ # This version does not run on multi-node # For apptainer rm -f results/benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json -apptainer 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 ${4} --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_tf32_iteration${5}.json'" +apptainer exec --nv --no-home -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 ${4} --logname='benchmark_dim${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 -apptainer 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 ${4} --amp --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json'" +apptainer exec --nv --no-home -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 ${4} --amp --logname='benchmark_dim${1}_nodes${2}_gpus${3}_batchsize${4}_amp_iteration${5}.json'" ###################22.11.0