re-train model with updated dints implementation

README.md

@@ -66,17 +66,17 @@ Dice score is used for evaluating the performance of the model. This model achie
 #### Training Loss
 The loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)
 
-![Training loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_train_4-2.png)
+![Training loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_train_4-3.png)
 
 #### Validation Dice
 The mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)
 
-![Validation mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_validation_4-2.png)
+![Validation mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_validation_4-3.png)
 
 ### Searched Architecture Visualization
-Users can install Graphviz for visualization of searched architectures (needed in custom/decode_plot.py). The edges between nodes indicate global structure, and numbers next to edges represent different operations in the cell searching space. An example of searched architecture is shown as follows:
+Users can install Graphviz for visualization of searched architectures (needed in [decode_plot.py](https://github.com/Project-MONAI/tutorials/blob/main/automl/DiNTS/decode_plot.py)). The edges between nodes indicate global structure, and numbers next to edges represent different operations in the cell searching space. An example of searched architecture is shown as follows:
 
-![Example of Searched Architecture](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_searched_arch_example.png)
+![Example of Searched Architecture](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_searched_arch_example_1.png)
 
 ## 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.
@@ -98,25 +98,25 @@ torchrun --nnodes=1 --nproc_per_node=8 -m scripts.search run --config_file confi
 #### Execute training:
 
 ```
-python -m monai.bundle run training --meta_file configs/metadata.json --config_file configs/train.yaml --logging_file configs/logging.conf
+python -m monai.bundle run --config_file configs/train.yaml
 ```
 
 #### Override the `train` config to execute multi-GPU training:
 
 ```
-torchrun --nnodes=1 --nproc_per_node=2 -m monai.bundle run training --meta_file configs/metadata.json --config_file "['configs/train.yaml','configs/multi_gpu_train.yaml']" --logging_file configs/logging.conf
+torchrun --nnodes=1 --nproc_per_node=8 -m monai.bundle run --config_file "['configs/train.yaml','configs/multi_gpu_train.yaml']"
 ```
 
 #### Override the `train` config to execute evaluation with the trained model:
 
 ```
-python -m monai.bundle run evaluating --meta_file configs/metadata.json --config_file "['configs/train.yaml','configs/evaluate.yaml']" --logging_file configs/logging.conf
+python -m monai.bundle run --config_file "['configs/train.yaml','configs/evaluate.yaml']"
 ```
 
 #### Execute inference:
 
 ```
-python -m monai.bundle run evaluating --meta_file configs/metadata.json --config_file configs/inference.yaml --logging_file configs/logging.conf
+python -m monai.bundle run --config_file configs/inference.yaml
 ```
 
 #### Export checkpoint for TorchScript

configs/evaluate.yaml

@@ -59,6 +59,7 @@ validate#handlers:
   - val_mean_dice
   batch_transform: "$monai.handlers.from_engine(['image_meta_dict'])"
   summary_ops: "*"
-evaluating:
+initialize:
 - "$setattr(torch.backends.cudnn, 'benchmark', True)"
+run:
 - "$@validate#evaluator.run()"

configs/inference.yaml

@@ -6,7 +6,7 @@ input_channels: 1
 output_classes: 3
 arch_ckpt_path: "$@bundle_root + '/models/search_code_18590.pt'"
 arch_ckpt: "$torch.load(@arch_ckpt_path, map_location=torch.device('cuda'))"
-bundle_root: "/workspace/MONAI/model-zoo/models/pancreas_ct_dints_segmentation"
+bundle_root: "."
 output_dir: "$@bundle_root + '/eval'"
 dataset_dir: "/workspace/data/msd/Task07_Pancreas"
 data_list_file_path: "$@bundle_root + '/configs/dataset_0.json'"
@@ -111,6 +111,7 @@ evaluator:
   postprocessing: "@postprocessing"
   val_handlers: "@handlers"
   amp: true
-evaluating:
+initialize:
 - "$setattr(torch.backends.cudnn, 'benchmark', True)"
+run:
 - "$@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": "0.3.6",
+    "version": "0.3.7",
     "changelog": {
+        "0.3.7": "re-train model with updated dints implementation",
         "0.3.6": "black autofix format and add name tag",
         "0.3.5": "restructure readme to match updated template",
         "0.3.4": "correct typos",
@@ -14,9 +15,9 @@
         "0.1.0": "complete the model package",
         "0.0.1": "initialize the model package structure"
     },
-    "monai_version": "1.0.1",
-    "pytorch_version": "1.13.0",
-    "numpy_version": "1.21.2",
+    "monai_version": "1.2.0rc4",
+    "pytorch_version": "1.13.1",
+    "numpy_version": "1.22.2",
     "optional_packages_version": {
         "fire": "0.4.0",
         "nibabel": "4.0.1",

configs/multi_gpu_train.yaml

@@ -26,14 +26,16 @@ train#handlers:
 train#trainer#max_epochs: "$400*dist.get_world_size()"
 train#trainer#train_handlers: "$@train#handlers[: -2 if dist.get_rank() > 0 else None]"
 validate#evaluator#val_handlers: "$None if dist.get_rank() > 0 else @validate#handlers"
-training:
+initialize:
 - "$import torch.distributed as dist"
-- "$dist.init_process_group(backend='nccl')"
+- "$dist.is_initialized() or dist.init_process_group(backend='nccl')"
 - "$torch.cuda.set_device(@device)"
 - "$monai.utils.set_determinism(seed=123)"
 - "$setattr(torch.backends.cudnn, 'benchmark', True)"
+run:
 - "$@train#trainer.run()"
-- "$dist.destroy_process_group()"
+finalize:
+- "$dist.is_initialized() and dist.destroy_process_group()"
 train_data_partition: "$monai.data.partition_dataset(data=@train_datalist, num_partitions=dist.get_world_size(),
   shuffle=True, even_divisible=True,)[dist.get_rank()]"
 train#dataset:

configs/train.yaml

@@ -9,7 +9,7 @@ input_channels: 1
 output_classes: 3
 arch_ckpt_path: "$@bundle_root + '/models/search_code_18590.pt'"
 arch_ckpt: "$torch.load(@arch_ckpt_path, map_location=torch.device('cuda'))"
-bundle_root: "/workspace/MONAI/model-zoo/models/pancreas_ct_dints_segmentation"
+bundle_root: "."
 ckpt_dir: "$@bundle_root + '/models'"
 output_dir: "$@bundle_root + '/eval'"
 dataset_dir: "/workspace/data/msd/Task07_Pancreas"
@@ -348,7 +348,7 @@ validate:
     additional_metrics: "@validate#additional_metrics"
     val_handlers: "@validate#handlers"
     amp: true
-training:
+initialize:
 - "$monai.utils.set_determinism(seed=123)"
-- "$setattr(torch.backends.cudnn, 'benchmark', True)"
+run:
 - "$@train#trainer.run()"

docs/README.md

@@ -59,17 +59,17 @@ Dice score is used for evaluating the performance of the model. This model achie
 #### Training Loss
 The loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)
 
-![Training loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_train_4-2.png)
+![Training loss over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_train_4-3.png)
 
 #### Validation Dice
 The mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)
 
-![Validation mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_validation_4-2.png)
+![Validation mean dice score over 3200 epochs (the bright curve is smoothed, and the dark one is the actual curve)](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_validation_4-3.png)
 
 ### Searched Architecture Visualization
-Users can install Graphviz for visualization of searched architectures (needed in custom/decode_plot.py). The edges between nodes indicate global structure, and numbers next to edges represent different operations in the cell searching space. An example of searched architecture is shown as follows:
+Users can install Graphviz for visualization of searched architectures (needed in [decode_plot.py](https://github.com/Project-MONAI/tutorials/blob/main/automl/DiNTS/decode_plot.py)). The edges between nodes indicate global structure, and numbers next to edges represent different operations in the cell searching space. An example of searched architecture is shown as follows:
 
-![Example of Searched Architecture](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_searched_arch_example.png)
+![Example of Searched Architecture](https://developer.download.nvidia.com/assets/Clara/Images/clara_pt_net_arch_search_segmentation_searched_arch_example_1.png)
 
 ## 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.
@@ -91,25 +91,25 @@ torchrun --nnodes=1 --nproc_per_node=8 -m scripts.search run --config_file confi
 #### Execute training:
 
 ```
-python -m monai.bundle run training --meta_file configs/metadata.json --config_file configs/train.yaml --logging_file configs/logging.conf
+python -m monai.bundle run --config_file configs/train.yaml
 ```
 
 #### Override the `train` config to execute multi-GPU training:
 
 ```
-torchrun --nnodes=1 --nproc_per_node=2 -m monai.bundle run training --meta_file configs/metadata.json --config_file "['configs/train.yaml','configs/multi_gpu_train.yaml']" --logging_file configs/logging.conf
+torchrun --nnodes=1 --nproc_per_node=8 -m monai.bundle run --config_file "['configs/train.yaml','configs/multi_gpu_train.yaml']"
 ```
 
 #### Override the `train` config to execute evaluation with the trained model:
 
 ```
-python -m monai.bundle run evaluating --meta_file configs/metadata.json --config_file "['configs/train.yaml','configs/evaluate.yaml']" --logging_file configs/logging.conf
+python -m monai.bundle run --config_file "['configs/train.yaml','configs/evaluate.yaml']"
 ```
 
 #### Execute inference:
 
 ```
-python -m monai.bundle run evaluating --meta_file configs/metadata.json --config_file configs/inference.yaml --logging_file configs/logging.conf
+python -m monai.bundle run --config_file configs/inference.yaml
 ```
 
 #### Export checkpoint for TorchScript

models/model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de79b954bb197c9a75d198c7b1038ad504cf0e370ae8b055c49c134c7b0e883
-size 534788757
+oid sha256:a18ae8b837f6affe778d7e9f130e6045c04a6f7d5b5dd8470155b9a18b6bcb65
+size 553830837

models/model.ts

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c47d9b4d1ec457dfa28c9e03c4ab847cdbe6ca825e3a84a245ca8a9caa631f
-size 534978281
+oid sha256:39d6087354fcff7b90e27191e5654774b98e6d7b503aa5752edfa9b07867bd5a
+size 554038651

models/search_code_18590.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a2a05b173e9a5a80a009ce4baa3dfd8118463e7c26a1ef49cce573a3e662cc
+oid sha256:5049f457b4cdbee036faf56ff5445c633300128d582731e6364c97fa3dc8a515
 size 4355