[DLMED] simplify to override

Signed-off-by: Nic Ma <[email protected]>

Author: Nic-Ma

modules/bundles/spleen_segmentation/configs/multi_gpu_train.json

@@ -0,0 +1,34 @@
+{
+    "device": "$torch.device(f'cuda:{dist.get_rank()}')",
+    "network": {
+        "_target_": "torch.nn.parallel.DistributedDataParallel",
+        "module": "$@network_def.to(@device)",
+        "device_ids": ["@device"]
+    },
+    "train#sampler": {
+        "_target_": "DistributedSampler",
+        "dataset": "@train#dataset",
+        "even_divisible": true,
+        "shuffle": true
+    },
+    "train#dataloader#sampler": "@train#sampler",
+    "train#dataloader#shuffle": false,
+    "train#trainer#train_handlers": "$@train#handlers[: 1 if dist.get_rank() > 0 else None]",
+    "validate#sampler": {
+        "_target_": "DistributedSampler",
+        "dataset": "@validate#dataset",
+        "even_divisible": false,
+        "shuffle": false
+    },
+    "validate#dataloader#sampler": "@validate#sampler",
+    "validate#evaluator#val_handlers": "$None if dist.get_rank() > 0 else @validate#handlers",
+    "training": [
+        "$import torch.distributed as dist",
+        "$dist.init_process_group(backend='nccl')",
+        "$torch.cuda.set_device(@device)",
+        "$monai.utils.set_determinism(seed=123)",
+        "$setattr(torch.backends.cudnn, 'benchmark', True)",
+        "$@train#trainer.run()",
+        "$dist.destroy_process_group()"
+    ]
+}

modules/bundles/spleen_segmentation/configs/train_multi_gpu.json

@@ -250,7 +250,7 @@
             "postprocessing": "@validate#postprocessing",
             "key_val_metric": "@validate#key_metric",
             "additional_metrics": "@validate#additional_metrics",
-            "val_handlers": "$@validate#handlers if dist.get_rank() > 0 else None",
+            "val_handlers": "$None if dist.get_rank() > 0 else @validate#handlers",
             "amp": true
         }
     },

modules/bundles/spleen_segmentation/docs/README.md

@@ -29,10 +29,10 @@ Execute training:
 python -m monai.bundle run training --meta_file configs/metadata.json --config_file configs/train.json --logging_file configs/logging.conf
 ```
 
-Execute multi-GPU training:
+Override the train config to execute multi-GPU training:
 
 ```
-torchrun --standalone --nnodes=1 --nproc_per_node=2 -m monai.bundle run training --meta_file configs/metadata.json --config_file configs/train_multi_gpu.json --logging_file configs/logging.conf
+torchrun --standalone --nnodes=1 --nproc_per_node=2 -m monai.bundle run training --meta_file configs/metadata.json --config_file configs/train.json --logging_file configs/logging.conf --args_file configs/multi_gpu_train.json
 ```
 
 Execute inference: