[WIP] Support Deepgrow 2D/3D Training

.github/ISSUE_TEMPLATE/question.md

@@ -0,0 +1,12 @@
+---
+name: Question
+about: Question relating to MONAI
+title: ''
+labels: ''
+assignees: ''
+---
+
+**Please use MONAI's Discussions tab**
+For questions relating to MONAI usage, please do not create an issue.
+
+Instead, use [MONAI's GitHub Discussions tab](https://github.com/Project-MONAI/MONAI/discussions). This can be found next to Issues and Pull Requests along the top of our repository.

.github/workflows/integration.yml

@@ -34,7 +34,7 @@ jobs:
         which python
         python -m pip install --upgrade pip wheel
         python -m pip uninstall -y torch torchvision
-        python -m pip install torch==1.7.0 torchvision==0.8.1
+        python -m pip install torch==1.7.1 torchvision==0.8.2
         python -m pip install -r requirements-dev.txt
     - name: Run integration tests
       run: |

.github/workflows/pythonapp.yml

@@ -80,13 +80,13 @@ jobs:
     - if: runner.os == 'windows'
       name: Install torch cpu from pytorch.org (Windows only)
       run: |
-        python -m pip install torch==1.7.0+cpu torchvision==0.8.1+cpu -f https://download.pytorch.org/whl/torch_stable.html
+        python -m pip install torch==1.7.1+cpu torchvision==0.8.2+cpu -f https://download.pytorch.org/whl/torch_stable.html
         # min. requirements for windows instances
         python -c "f=open('requirements-dev.txt', 'r'); txt=f.readlines(); f.close(); print(txt); f=open('requirements-dev.txt', 'w'); f.writelines(txt[1:12]); f.close()"
     - name: Install the dependencies
       run: |
-        python -m pip install torch==1.7.0
-        python -m pip install torchvision==0.8.1
+        python -m pip install torch==1.7.1
+        python -m pip install torchvision==0.8.2
         cat "requirements-dev.txt"
         python -m pip install -r requirements-dev.txt
         python -m pip list
@@ -108,7 +108,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [windows-latest, macOS-latest, ubuntu-latest]
-    timeout-minutes: 20
+    timeout-minutes: 40
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python 3.8
@@ -134,11 +134,11 @@ jobs:
     - if: runner.os == 'windows'
       name: Install torch cpu from pytorch.org (Windows only)
       run: |
-        python -m pip install torch==1.7.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
+        python -m pip install torch==1.7.1+cpu -f https://download.pytorch.org/whl/torch_stable.html
     - name: Install the dependencies
       run: |
         # min. requirements
-        python -m pip install torch==1.7.0
+        python -m pip install torch==1.7.1
         python -m pip install -r requirements-min.txt
         python -m pip list
         BUILD_MONAI=0 python setup.py develop  # no compile of extensions
@@ -173,7 +173,7 @@ jobs:
             pytorch: "-h"
             base: "nvcr.io/nvidia/pytorch:20.07-py3"
           - environment: PT17+CUDA102
-            pytorch: "torch==1.7.0 torchvision==0.8.1"
+            pytorch: "torch==1.7.1 torchvision==0.8.2"
             base: "nvcr.io/nvidia/cuda:10.2-devel-ubuntu18.04"
           - environment: PT17+CUDA110
             # we explicitly set pytorch to -h to avoid pip install error

.github/workflows/setupapp.yml

@@ -36,7 +36,7 @@ jobs:
         which python
         python -m pip install --upgrade pip wheel
         python -m pip uninstall -y torch torchvision
-        python -m pip install torch==1.7.0 torchvision==0.8.1
+        python -m pip install torch==1.7.1 torchvision==0.8.2
         python -m pip install -r requirements-dev.txt
     - name: Run unit tests report coverage
       run: |
@@ -82,7 +82,7 @@ jobs:
     - name: Install the dependencies
       run: |
         python -m pip install --upgrade pip wheel
-        python -m pip install torch==1.7.0 torchvision==0.8.1
+        python -m pip install torch==1.7.1 torchvision==0.8.2
         python -m pip install -r requirements-dev.txt
     - name: Run quick tests CPU ubuntu
       run: |
@@ -151,7 +151,8 @@ jobs:
       run: |
         docker build -t localhost:5000/local_monai:latest -f Dockerfile .
         docker push localhost:5000/local_monai:latest
-        docker tag localhost:5000/local_monai:latest projectmonai/monai:latest
+        sed -i '/flake/d' requirements-dev.txt
+        docker build -t projectmonai/monai:latest -f Dockerfile .
         docker login -u projectmonai -p ${{ secrets.DOCKER_PW }}
         docker push projectmonai/monai:latest
         docker logout

.github/workflows/weekly-preview.yml

@@ -29,7 +29,7 @@ jobs:
         git config user.email "monai.miccai2019@gmail.com"
         git add setup.cfg monai/__init__.py
         git commit -m "Weekly build at $HEAD_COMMIT_ID"
-        git tag 0.4.dev$(date +'%y%U')
+        git tag 0.5.dev$(date +'%y%U')
         python setup.py sdist bdist_wheel
 
     - name: Publish to PyPI

CHANGELOG.md

@@ -5,6 +5,77 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+## [0.4.0] - 2020-12-15
+### Added
+* Overview document for [feature highlights in v0.4.0](https://github.com/Project-MONAI/MONAI/blob/master/docs/source/highlights.md)
+* Torchscript support for the net modules
+* New networks and layers:
+  * Discrete Gaussian kernels
+  * Hilbert transform and envelope detection
+  * Swish and mish activation
+  * Acti-norm-dropout block
+  * Upsampling layer
+  * Autoencoder, Variational autoencoder
+  * FCNet
+* Support of initialisation from pretrained weights for densenet, senet, multichannel AHNet
+* Layer-wise learning rate API
+* New model metrics and event handlers based on occlusion sensitivity, confusion matrix, surface distance
+* CAM/GradCAM/GradCAM++
+* File format-agnostic image loader APIs with Nibabel, ITK readers
+* Enhancements for dataset partition, cross-validation APIs
+* New data APIs:
+  * LMDB-based caching dataset
+  * Cache-N-transforms dataset
+  * Iterable dataset
+  * Patch dataset
+* Weekly PyPI release
+* Fully compatible with PyTorch 1.7
+* CI/CD enhancements:
+  * Skipping, speed up, fail fast, timed, quick tests
+  * Distributed training tests
+  * Performance profiling utilities
+* New tutorials and demos:
+  * Autoencoder, VAE tutorial
+  * Cross-validation demo
+  * Model interpretability tutorial
+  * COVID-19 Lung CT segmentation challenge open-source baseline
+  * Threadbuffer demo
+  * Dataset partitioning tutorial
+  * Layer-wise learning rate demo
+  * [MONAI Bootcamp 2020](https://github.com/Project-MONAI/MONAIBootcamp2020)
+
+### Changed
+* Base Docker image upgraded to `nvcr.io/nvidia/pytorch:20.10-py3` from `nvcr.io/nvidia/pytorch:20.08-py3`
+
+#### Backwards Incompatible Changes
+* `monai.apps.CVDecathlonDataset` is extended to a generic `monai.apps.CrossValidation` with an `dataset_cls` option
+* Cache dataset now requires a `monai.transforms.Compose` instance as the transform argument
+* Model checkpoint file name extensions changed from `.pth` to `.pt`
+* Readers' `get_spatial_shape` returns a numpy array instead of list
+* Decoupled postprocessing steps such as `sigmoid`, `to_onehot_y`, `mutually_exclusive`, `logit_thresh` from metrics and event handlers,
+the postprocessing steps should be used before calling the metrics methods
+* `ConfusionMatrixMetric` and `DiceMetric` computation now returns an additional `not_nans` flag to indicate valid results
+* `UpSample` optional `mode` now supports `"deconv"`, `"nontrainable"`, `"pixelshuffle"`; `interp_mode` is only used when `mode` is `"nontrainable"`
+* `SegResNet` optional `upsample_mode` now supports `"deconv"`, `"nontrainable"`, `"pixelshuffle"`
+* `monai.transforms.Compose` class inherits `monai.transforms.Transform`
+* In `Rotate`, `Rotated`, `RandRotate`, `RandRotated`  transforms, the `angle` related parameters are interpreted as angles in radians instead of degrees.
+* `SplitChannel` and `SplitChanneld` moved from `transforms.post` to `transforms.utility`
+
+### Removed
+* Support of PyTorch 1.4
+
+### Fixed
+* Enhanced loss functions for stability and flexibility
+* Sliding window inference memory and device issues
+* Revised transforms:
+  * Normalize intensity datatype and normalizer types
+  * Padding modes for zoom
+  * Crop returns coordinates
+  * Select items transform
+  * Weighted patch sampling
+  * Option to keep aspect ratio for zoom
+* Various CI/CD issues
+
 ## [0.3.0] - 2020-10-02
 ### Added
 * Overview document for [feature highlights in v0.3.0](https://github.com/Project-MONAI/MONAI/blob/master/docs/source/highlights.md)
@@ -102,7 +173,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 [highlights]: https://github.com/Project-MONAI/MONAI/blob/master/docs/source/highlights.md
 
-[Unreleased]: https://github.com/Project-MONAI/MONAI/compare/0.3.0...HEAD
+[Unreleased]: https://github.com/Project-MONAI/MONAI/compare/0.4.0...HEAD
+[0.4.0]: https://github.com/Project-MONAI/MONAI/compare/0.3.0...0.4.0
 [0.3.0]: https://github.com/Project-MONAI/MONAI/compare/0.2.0...0.3.0
 [0.2.0]: https://github.com/Project-MONAI/MONAI/compare/0.1.0...0.2.0
 [0.1.0]: https://github.com/Project-MONAI/MONAI/commits/0.1.0

CONTRIBUTING.md

@@ -32,6 +32,8 @@ _Pull request early_
 
 We encourage you to create pull requests early. It helps us track the contributions under development, whether they are ready to be merged or not. Change your pull request's title to begin with `[WIP]` until it is ready for formal review.
 
+Please note that, as per PyTorch, MONAI uses American English spelling. This means classes and variables should be: normali**z**e, visuali**z**e, colo~~u~~r, etc.
+
 ### Preparing pull requests
 To ensure the code quality, MONAI relies on several linting tools ([flake8 and its plugins](https://gitlab.com/pycqa/flake8), [black](https://github.com/psf/black), [isort](https://github.com/timothycrosley/isort)),
 static type analysis tools ([mypy](https://github.com/python/mypy), [pytype](https://github.com/google/pytype)), as well as a set of unit/integration tests.

README.md

@@ -61,7 +61,7 @@ For guidance on making a contribution to MONAI, see the [contributing guidelines
 ## Community
 Join the conversation on Twitter [@ProjectMONAI](https://twitter.com/ProjectMONAI) or join our [Slack channel](https://forms.gle/QTxJq3hFictp31UM9).
 
-Ask and answer questions over on the [PyTorch Forums](https://discuss.pytorch.org/) or [StackOverflow](https://stackoverflow.com/tags/monai). Make sure to tag @monai.
+Ask and answer questions over on [MONAI's GitHub Discussions tab](https://github.com/Project-MONAI/MONAI/discussions).
 
 ## Links
 - Website: https://monai.io/

docs/source/handlers.rst

@@ -34,12 +34,24 @@ ROC AUC metrics handler
     :members:
 
 
-Confusion Matrix metrics handler
+Confusion matrix metrics handler
 --------------------------------
 .. autoclass:: ConfusionMatrix
     :members:
 
 
+Hausdorff distance metrics handler
+----------------------------------
+.. autoclass:: HausdorffDistance
+    :members:
+
+
+Surface distance metrics handler
+--------------------------------
+.. autoclass:: SurfaceDistance
+    :members:
+
+
 Metric logger
 -------------
 .. autoclass:: MetricLogger