deterministic retrain benchmark and add link

README.md

@@ -114,14 +114,13 @@ This model achieves the following Dice score on the validation data provided as
 #### Training Loss and Dice
 A graph showing the training Loss and Dice over 50 epochs.
 
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss.jpeg) <br>
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice.jpeg) <br>
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss_v2.png) <br>
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice_v2.png) <br>
 
 #### Validation Dice
 A graph showing the validation mean Dice over 50 epochs.
 
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice.jpeg) <br>
-
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice_v2.png) <br>
 
 ## MONAI Bundle Commands
 In addition to the Pythonic APIs, a few command line interfaces (CLI) are provided to interact with the bundle. The CLI supports flexible use cases, such as overriding configs at runtime and predefining arguments in a file.

configs/evaluate.json

@@ -49,11 +49,6 @@
             "summary_ops": "*"
         }
     ],
-    "initialize": [
-        "$import sys",
-        "$sys.path.append(@bundle_root)",
-        "$setattr(torch.backends.cudnn, 'benchmark', True)"
-    ],
     "run": [
         "$@validate#evaluator.run()"
     ]

configs/inference.json

@@ -124,7 +124,9 @@
         "amp": true
     },
     "initialize": [
-        "$setattr(torch.backends.cudnn, 'benchmark', True)"
+        "$import sys",
+        "$sys.path.append(@bundle_root)",
+        "$monai.utils.set_determinism(seed=123)"
     ],
     "run": [
         "$@evaluator.run()"

configs/metadata.json

@@ -1,7 +1,8 @@
 {
     "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
-    "version": "0.1.0",
+    "version": "0.1.1",
     "changelog": {
+        "0.1.1": "deterministic retrain benchmark and add link",
         "0.1.0": "fix mgpu finalize issue",
         "0.0.9": "Update README Formatting",
         "0.0.8": "enable deterministic training",

configs/multi_gpu_evaluate.json

@@ -21,6 +21,7 @@
         "$import torch.distributed as dist",
         "$dist.is_initialized() or dist.init_process_group(backend='nccl')",
         "$torch.cuda.set_device(@device)",
+        "$monai.utils.set_determinism(seed=123)",
         "$import logging",
         "$@validate#evaluator.logger.setLevel(logging.WARNING if dist.get_rank() > 0 else logging.INFO)"
     ],

docs/README.md

@@ -107,14 +107,13 @@ This model achieves the following Dice score on the validation data provided as
 #### Training Loss and Dice
 A graph showing the training Loss and Dice over 50 epochs.
 
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss.jpeg) <br>
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice.jpeg) <br>
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss_v2.png) <br>
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice_v2.png) <br>
 
 #### Validation Dice
 A graph showing the validation mean Dice over 50 epochs.
 
-![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice.jpeg) <br>
-
+![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice_v2.png) <br>
 
 ## MONAI Bundle Commands
 In addition to the Pythonic APIs, a few command line interfaces (CLI) are provided to interact with the bundle. The CLI supports flexible use cases, such as overriding configs at runtime and predefining arguments in a file.

models/model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9886629a19d2f3ef2d607d156f1c9409d32d193a7b831d19df35cf4cf303aebe
+oid sha256:e40ca4d2a5e8649d9faef3aa9a0ec6fa201526d0262a4bc63431a151b178a8ae
 size 31162823