diff --git a/README.md b/README.md index 6c8d2bdb2131c9b2167eaff0da173bf74d392842..8a8402ff558b7a52a543d4ca35bbcf4e702513b9 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,7 @@ cd ~/DeepLearningExamples/nnunet_for_pytorch_$VERSION/ ``` - Build the nnU-Net PyTorch Docker container +Change the pytorch-lightning version to 1.5.10 to avoid the `from torchmetrics.utilities.data import get_num_classes as _get_num_classes` error. ``` docker build -t nnunet . ``` @@ -67,7 +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 +cd Berzelius-nnU-Net-Benchmark && mkdir -p sbatch_out bash scripts/benchmark_sbatch_submit.sh 2 1 8 1 128 ```