Skip to main content

Browse the archive

https://github.com/Project-MONAI/MONAI/
22 March 2024, 02:43:53 UTC
sort by:
Revision Author Date Message Commit Date
52a7fde Wenqi Li 21 October 2022, 12:15:58 UTC skip test.pypi.org Signed-off-by: Wenqi Li <wenqil@nvidia.com> 21 October 2022, 12:15:58 UTC
8a7747d Wenqi Li 21 October 2022, 11:49:33 UTC releasing test py310 Signed-off-by: Wenqi Li <wenqil@nvidia.com> 21 October 2022, 11:49:33 UTC
f6325e2 Wenqi Li 21 October 2022, 11:41:00 UTC adding premerge tests for py3.10 (#5370) ### Description adding tests for python 3.10 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 21 October 2022, 11:48:07 UTC
4609206 Mingxin Zheng 20 October 2022, 16:41:31 UTC Remove meta_dict and fix affine to spacing conversion (#5367) Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Fixes #5201 Fixes #5332 ### Description - Remove deprecated meta_dict usage from Auto3DSeg. - Fix affine -> spacing conversion - Update docstring - Change "pixel_percentage" to "foreground_percentage" to unify foreground "pixel"/"voxel" naming ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] In-line docstrings updated. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> 20 October 2022, 17:03:52 UTC
9c423b6 Holger Roth 20 October 2022, 13:57:27 UTC update fl docs (#5364) Signed-off-by: Holger Roth <hroth@nvidia.com> Fixes #5363. ### Description Update what's new and module description with new Monai FL features. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 20 October 2022, 17:03:44 UTC
10ab34a myron 19 October 2022, 12:49:16 UTC str2list utility for commandline parsing of comma separated lists (#5358) This adds a utility function str2list to convert a string to a list. Useful with argparse commandline arguments: ``` parser.add_argument("--blocks", default=[1,2,3], type=str2list) ... python mycode.py --blocks=1,2,2,4 ``` Unit tests added. It also includes a small fix for str2bool to accept input as bool (and return it right away). ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ x Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x]Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 19 October 2022, 13:03:08 UTC
652511f Holger Roth 19 October 2022, 10:58:07 UTC MonaiAlgo: fix logging in multi-gpu training (#5355) Signed-off-by: Holger Roth <hroth@nvidia.com> Fixes #5354. ### Description Previous output: ``` Current output: 2022-10-18 12:45:59,679 - MonaiAlgo - INFO - Using multi-gpu training on rank 1 (available devices: 2) 2022-10-18 12:45:59,681 - MonaiAlgo - INFO - Using multi-gpu training on rank 0 (available devices: 2) 2022-10-18 12:49:48,790 - ignite.engine.engine.SupervisedTrainer - INFO - Got new best metric of train_accuracy: 0.802879669048168 2022-10-18 12:49:48,790 - ignite.engine.engine.SupervisedTrainer - INFO - Got new best metric of train_accuracy: 0.802879669048168 2022-10-18 12:49:56,579 - ignite.engine.engine.SupervisedEvaluator - INFO - Got new best metric of val_mean_dice: 0.1470419466495514 2022-10-18 12:49:56,579 - ignite.engine.engine.SupervisedEvaluator - INFO - Got new best metric of val_mean_dice: 0.1470419466495514 ``` Output after fix: ``` 2022-10-18 12:51:05,400 - MonaiAlgo - INFO - Using multi-gpu training on rank 0 (available devices: 2) 2022-10-18 12:51:05,410 - MonaiAlgo - INFO - Using multi-gpu training on rank 1 (available devices: 2) 2022-10-18 12:53:09,889 - ignite.engine.engine.SupervisedTrainer - INFO - Got new best metric of train_accuracy: 0.6750877521656178 2022-10-18 12:53:25,170 - ignite.engine.engine.SupervisedEvaluator - INFO - Got new best metric of val_mean_dice: 0.06980131566524506 ``` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 19 October 2022, 13:01:55 UTC
9e444d4 myron 18 October 2022, 18:52:38 UTC Enhancement for WarmupCosineSchedule to specify the beginning fraction of the linear warmup (#5351) small enhancement to WarmupCosineSchedule input, to optionally specify the beginning of the linear warmup from something above 0 ( e.g from a fraction 0.1 * initial_lr). a unit test is added too. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 18 October 2022, 18:58:09 UTC
ba5fea2 Wenqi Li 17 October 2022, 18:00:25 UTC 5345 update output devices slidingwindow (#5346) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5345 sliding window output should prefer `device` instead of `inputs.device` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 18 October 2022, 10:22:22 UTC
e1d7a2e Wenqi Li 18 October 2022, 10:20:39 UTC skip test if no downloading Signed-off-by: Wenqi Li <wenqil@nvidia.com> 18 October 2022, 10:22:18 UTC
c0e3fa8 Wenqi Li 17 October 2022, 11:21:11 UTC skip cache for releasing branch; update test info Signed-off-by: Wenqi Li <wenqil@nvidia.com> 17 October 2022, 11:43:10 UTC
ee04909 Wenqi Li 17 October 2022, 11:13:21 UTC 5284 Fixes release integration tests (#5342) part of #5284 fixes incorrect ignite version used https://github.com/Project-MONAI/MONAI/actions/runs/3262265183 fixes autorunner test error: https://github.com/Project-MONAI/MONAI/actions/runs/3255478854/jobs/5347066136 fixes https://github.com/Project-MONAI/MONAI/issues/5343 ### Description tests are fixed by upgrading dep version and moving `test_auto3dseg_autorunner` unit test to `test_integration_autorunner` integration test. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 17 October 2022, 11:15:18 UTC
59fb2c3 Holger Roth 15 October 2022, 10:48:04 UTC MonaiAlgo FedStats (#5240) Fixes #5196, #5316. ### Description Add api function that allows FL systems to request summary statistics, i.e. `get_data_stats` in new `ClientStats` class. `MonaiStats` is added to provide implementation based on Monai bundle. Utilizes DataAnalyzer functions from Auto3DSeg. Changes to DataAnalyzer are supposed to not change the behavior. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 15 October 2022, 11:00:25 UTC
50749ec myron 15 October 2022, 09:00:55 UTC Dicece check for float target (#5326) Fixes https://github.com/Project-MONAI/tutorials/issues/987 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 15 October 2022, 09:30:19 UTC
7c3e838 Wenqi Li 14 October 2022, 18:46:03 UTC adding a multigpu test of TestFLMonaiAlgo (#5327) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes https://github.com/Project-MONAI/MONAI/issues/5133 ### Description adds a test ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 15 October 2022, 09:29:43 UTC
fe5a3bf Maxime-Perret 14 October 2022, 06:36:03 UTC Command format fix with backslashes on Windows System (#5280) Fixes MONAI/apps/Auto3DSeg/bundle_gen.py ### Description Commands ran in subprocess currently cause issues with string formatting and backslashes not being escaped properly. Changing from Back Flash to Forward Slash solves the issue. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Maxime <maxime.perret@epfl.ch> Signed-off-by: Mingxin Zheng <mingxinz@nvidia.com> Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Co-authored-by: Maxime <maxime.perret@epfl.ch> Co-authored-by: Mingxin Zheng <mingxin.zheng@philips.com> Co-authored-by: Mingxin Zheng <mingxinz@nvidia.com> Co-authored-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com 15 October 2022, 09:29:36 UTC
9d43d19 myron 13 October 2022, 22:06:15 UTC SlidingWindowInferer: option to adaptively stitch in cpu memory for large images (#5297) SlidingWindowInferer: option to adaptively stitch in cpu memory for large images. This adds an option to provide maximum input image volume (number of elements) to dynamically change stitching to cpu memory (to avoid gpu memory crashes). For example with `cpu_thresh=400*400*400`, all input images with large volume will be stitched on cpu. At the moment, a user must decide beforehand, to stitch ALL images on cpu or gpu (by specifying the 'device' parameter). But in many datasets, only a few large images require device==cpu, and running inference on cpu for ALL will be unnecessary slow. It's related to https://github.com/Project-MONAI/MONAI/discussions/4625 https://github.com/Project-MONAI/MONAI/discussions/4495 https://github.com/Project-MONAI/MONAI/discussions/3497 https://github.com/Project-MONAI/MONAI/discussions/4726 https://github.com/Project-MONAI/MONAI/discussions/4588 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 15 October 2022, 09:29:15 UTC
258f3ca myron 13 October 2022, 20:03:31 UTC Segresnet improvements (#5281) This adds improvements to SegResNet semantic segmentation to include deep supervision feature (among other things). I've decided to add a new network named SegResnetDS instead of replacing the existing SegResNet, because it would have broken all previously pretrained model checkpoints. Please take a look, and if it looks good, I can add unit tests. All the helper functions, and blocks are inside of the same file (which I prefer, since it's easier to read) instead of spreading it among other files (e.g segresnet_ds_block or segresnet_utils). ### Description A few sentences describing the changes proposed in this pull request. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 15 October 2022, 09:29:06 UTC
2b455e3 Dženan Zukić 13 October 2022, 19:21:10 UTC Fix installation verification command (#5328) Current command did not work on my machine: ```batch M:\Dev\MONAI>python -c 'import monai; monai.config.print_config()' File "<string>", line 1 'import ^ SyntaxError: EOL while scanning string literal M:\Dev\MONAI>python -c "import monai; monai.config.print_config()" MONAI version: 1.0.0+39.g9355f1c2 Numpy version: 1.23.4 Pytorch version: 1.12.1+cu113 MONAI flags: HAS_EXT = False, USE_COMPILED = False, USE_META_DICT = False MONAI rev id: 9355f1c264c7e69e28b005b8e8eb65c26e0c4ab0 MONAI __file__: M:\Dev\MONAI\monai\__init__.py Optional dependencies: Pytorch Ignite version: NOT INSTALLED or UNKNOWN VERSION. Nibabel version: NOT INSTALLED or UNKNOWN VERSION. scikit-image version: NOT INSTALLED or UNKNOWN VERSION. Pillow version: 9.2.0 Tensorboard version: NOT INSTALLED or UNKNOWN VERSION. gdown version: NOT INSTALLED or UNKNOWN VERSION. TorchVision version: 0.13.1+cu113 tqdm version: NOT INSTALLED or UNKNOWN VERSION. lmdb version: NOT INSTALLED or UNKNOWN VERSION. psutil version: NOT INSTALLED or UNKNOWN VERSION. pandas version: NOT INSTALLED or UNKNOWN VERSION. einops version: NOT INSTALLED or UNKNOWN VERSION. transformers version: NOT INSTALLED or UNKNOWN VERSION. mlflow version: NOT INSTALLED or UNKNOWN VERSION. pynrrd version: NOT INSTALLED or UNKNOWN VERSION. For details about installing the optional dependencies, please visit: https://docs.monai.io/en/latest/installation.html#installing-the-recommended-dependencies M:\Dev\MONAI> ``` 15 October 2022, 09:28:56 UTC
dd49e37 Wenqi Li 13 October 2022, 13:22:37 UTC tutorial 982 984 fixes occ sens, 987 ce loss (#5323) Signed-off-by: Wenqi Li <wenqil@nvidia.com> fixes https://github.com/Project-MONAI/tutorials/issues/982 fixes https://github.com/Project-MONAI/tutorials/issues/984 fixes https://github.com/Project-MONAI/tutorials/issues/987 ### Description robust mask size and grid ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 13 October 2022, 14:59:11 UTC
1e74bd6 monai-bot 13 October 2022, 09:47:02 UTC auto updates (#5322) Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> 13 October 2022, 14:59:02 UTC
ef6fe38 monai-bot 13 October 2022, 06:45:22 UTC auto updates (#5321) Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Signed-off-by: Wenqi Li <wenqil@nvidia.com> 13 October 2022, 14:57:24 UTC
a215ea6 myron 12 October 2022, 19:02:12 UTC fixes DiceCELoss for multichannel targets (#5292) Fixes DiceCELoss for multichannel targets. Currently if "target" (ground truth label) is provided as a multichannel data (each channel is binary or float), then current DiceCELoss attempts to convert it to 1-channel using argmax (which could be impossible with overlapping labels). There is no need for argmax, since pytorch's cross entropy can handle multi-channel targets already. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 12 October 2022, 19:25:56 UTC
c77521e myron 12 October 2022, 09:49:24 UTC updates to Gaussian map for sliding window inference (#5302) This updates the calculation of Gaussian map (weights) during sliding window inference with "gaussian" Current version had multiple small issues - it computed Gaussian weight map (image) via nn.Conv1d sequence with an empty image (with a single 1 in the middle). We don't need to run any convolutions, it's much simpler to directly calculate the Gaussian map (it's also faster and takes less memory) - For patch_sizes of even size (e.g. 128x128) it centered Gaussian on patch_size//2 which is 0.5 pixel off-center (I'm not sure why we did it. - Finally the Gaussian 1d convolutions were done approximately (with 'erf' internal approximation and truncated to sigma=4). I'm not sure why we need any approximations here at all, it's trivial to compute the Gaussian weight map directly ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 12 October 2022, 11:45:43 UTC
d1fafc4 Mingxin Zheng 11 October 2022, 12:13:46 UTC [ReadyForReview] Auto3DSeg DataAnalyzer OOM and other minor issue (#5278) Fixes #5277 . ### Updated results In my local test env, I have the following results: - The change of GPU memory before/after DataAnalyzer is less than 5MB after the fix. Previously, there are lots of cached PyTorch tensors and CuPy variables that are not released for trainings that takes up to several GBs of GPU mem. - DataAnalyzer can also process larger images now because leaks are fix (3D image with a size 512x512x512 passed for 12GB RTX 3080Ti) ### Description Auto3DSeg DataAnalyzer occupied a large trunk of memory and was unable to release them during the training. The reasons behind are possibly due to: - Training are done by subprocess call, and PyTorch in the subprocess is unable to find the memory pool allocated by the main process - GPU memory leakage ( DataAnalyzer math operations uses torch functions and CuPy) plus test functions need improvements and AutoRunner needs to expose the API call to change device of DataAnalyzer ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> 11 October 2022, 12:50:01 UTC
f040ec0 Nic Ma 11 October 2022, 11:02:45 UTC 5269 5291 Update PyTorch base docker to 22.09 (#5293) Fixes #5269 #5291 . ### Description This PR updated the PyTorch base docker to 22.09. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Nic Ma <nma@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com> 11 October 2022, 12:49:53 UTC
9fa35cc Yiheng Wang 10 October 2022, 18:32:31 UTC 5304 Add authenticated option for bundle api (#5306) Signed-off-by: Yiheng Wang <vennw@nvidia.com> Fixes #5304 . ### Description This PR adds the authenticated option for bundle api, which the authenticated token, users can increase their rate limits when using our bundle APIs. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Yiheng Wang <vennw@nvidia.com> 11 October 2022, 12:49:44 UTC
f6f6529 Wenqi Li 10 October 2022, 17:08:26 UTC fixes cherrypicking issues of spacing Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 17:08:26 UTC
b61b21e Wenqi Li 09 October 2022, 15:08:50 UTC 4206 adds ext tests and deps (#4207) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #4206 ### Description Currently ninja+jit is not tested on the cpu-only cases, this adds ninja (optional dep.) and premerge tests on ubuntu for ninja + jit extension. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:58:01 UTC
9b09863 binliunls 08 October 2022, 18:51:57 UTC 5187 update the docstring of the is_pad parameter (#5296) Signed-off-by: binliu <binliu@nvidia.com> Fixes #5187 . ### Description Updated the docstring of the is_pad parameter in flexible-unet. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: binliu <binliu@nvidia.com> 10 October 2022, 12:58:01 UTC
5a517fb myron 08 October 2022, 18:08:18 UTC Upsample mode deconvgroup (#5282) This adds an additional UpSample mode DECONVGROUP to upsample with groupwise convolution transpose. Unit tests are passed too. A few sentences describing the changes proposed in this pull request. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 10 October 2022, 12:58:01 UTC
eb0795e TrellixVulnTeam 06 October 2022, 07:56:23 UTC CVE-2007-4559 Patch (#5274) # Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this [blog](https://www.trellix.com/en-us/about/newsroom/stories/research/tarfile-exploiting-the-world.html). If you have further questions you may contact us through this projects lead researcher [Kasimir Schulz](mailto:kasimir.schulz@trellix.com). Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 10 October 2022, 12:58:01 UTC
c9d1a71 Wenqi Li 05 October 2022, 11:24:54 UTC 4320 update docstrings for gradient based saliency (#5268) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #4320 it seems we also have sufficient modules to close #3542 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:58:01 UTC
d76adc7 Wenqi Li 04 October 2022, 13:58:30 UTC 5253 fixes output offset - spacing (#5254) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5253 ### Description enhance computing offset for spacing ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:58:00 UTC
94673a9 pre-commit-ci[bot] 04 October 2022, 11:47:29 UTC [pre-commit.ci] pre-commit suggestions/consolidate autofixes (#5256) <!--pre-commit.ci start--> updates: - [github.com/asottile/pyupgrade: v2.34.0 → v2.38.2](https://github.com/asottile/pyupgrade/compare/v2.34.0...v2.38.2) - [github.com/asottile/yesqa: v1.3.0 → v1.4.0](https://github.com/asottile/yesqa/compare/v1.3.0...v1.4.0) - [github.com/hadialqattan/pycln: v1.3.5 → v2.1.1](https://github.com/hadialqattan/pycln/compare/v1.3.5...v2.1.1) <!--pre-commit.ci end--> Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:58:00 UTC
1ee8ba0 Can Zhao 03 October 2022, 20:02:16 UTC fix bug in retina detector (#5255) Signed-off-by: Can Zhao <canz@nvidia.com> Fixes #5250. ### Description Fixed bug that allow_low_quality_matches in set_regular_matcher was always set to True and it's not using value from the argument, in retinanet. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Can Zhao <canz@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 10 October 2022, 12:58:00 UTC
6e63284 Wenqi Li 03 October 2022, 15:30:33 UTC 5251 replace None type metadict content with 'none' (#5252) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5251 ### Description replace `None` with `"none"` in the readers ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:58:00 UTC
2687b72 myron 01 October 2022, 15:04:05 UTC UpSample optional kernel_size for deconv mode (#5221) ### Description Adds (optional) kernel_size parameter to UpSample, used for deconv (convolution transpose up-sampling). This allows to upsample, e.g to upscale to 2x with a kernel_size 3. (currently the default is to upscale to 2x with a kernel size 2) if this parameter is not set, the behavior is the same as before ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: myron <amyronenko@nvidia.com> 10 October 2022, 12:58:00 UTC
68d1b34 Richard Brown 30 September 2022, 16:29:27 UTC Occlusion sensitivity to use slidiing_window_inference (#5230) ### Description Occlusion sensitivity currently works by setting the logits at the center of the occluded region. Even though neighbouring voxels are occluded at the same time, this is not recorded. A better way to do it would be to do an average each time a voxel is occluded. This is taken care of by switching to using `sliding_window_inference`. We had to do a bit of hacking to get this to work. `sliding_window_inference` normally takes a subset of the whole image and infers that. We want `sliding_window_inference` to tell us which part of the image we should occlude, then we occlude it and infer the **whole** image. To that end, we use a meshgrid to tell us the coordinates of the region `sliding_window_inference` wants us to occlude. We occlude, infer and then crop back to the size of the region that was requested by `sliding_window_inference`. This PR also allows for different occlusion kernels. We currently have: - gaussian (actually inverse gaussian): the center of the occluded region is zero, and towards the edge of the image is unchanged. This doesn't introduce hard edges into the image, which might undermine the visualisation process. - mean_patch: the occluded region is replaced with the mean of the patch it is occluding. - mean_img: the occluded region is replaced with the mean of the whole image (current implementation). ## Changes to input arguments This PR is backwards incompatible, as using `sliding_window_inference` means changing the API significantly. - pad_val: now determined by `mode` - stride: `overlap` used instead - per_channel: all channels are done simultaneously - upsampler: image is no longer downsampled ## Changes to output Output previously had the shape `B,C,H,W,[D],N` where `C` and `N` were the number of input and output channels of the network, respectively. Now, we output the shape `B,N,H,W,[D]` as the `per_channel` feature is no longer present. Columns 2-4 are occlusion sensitivity done with Gaussian, mean of patch and mean of image: ![vis](https://user-images.githubusercontent.com/33289025/193261000-b879bce8-3aab-433b-af6c-cbb9c885d0a3.png) ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> 10 October 2022, 12:57:59 UTC
e8879a0 Behrooz Hashemian 30 September 2022, 15:24:44 UTC HoVerNet Mode and Branch to independent StrEnum (#5219) Fixes #5218 ### Description This PR moves `HoVerNet` Mode and Branch outside of the module and make them independent `StrEnums`. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 10 October 2022, 12:57:59 UTC
21e0ad5 Holger Roth 30 September 2022, 14:25:10 UTC Add multi-gpu support to MonaiAlgo (#5228) Signed-off-by: Holger Roth <hroth@nvidia.com> Fixes #5195. ### Description Add support for MonaiAlgo to be run with torchrun for multi-gpu training. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 10 October 2022, 12:57:59 UTC
06aee55 macdavid 30 September 2022, 12:44:38 UTC Solve LoadImage issue when track_meta is False (#5239) 1. Fix the issue #5227 2. fix a small code flaw Signed-off-by: David <dyq.004@gmail.com> 10 October 2022, 12:57:59 UTC
df84c3d YunLiu 30 September 2022, 10:13:51 UTC Fix 1D data error in `VarAutoEncoder` (#5236) Signed-off-by: KumoLiu <yunl@nvidia.com> Fixes #5225 . ### Description 1. fix 1d data error in `VarAutoEncoder` 2. add `use_sigmoid` flag ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: KumoLiu <yunl@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 10 October 2022, 12:57:58 UTC
b862c75 Nic Ma 30 September 2022, 08:07:42 UTC 5233 Add file check for the logging config (#5235) Fixes #5233 . ### Description This PR added file existing check for the logging config, requested by @holgerroth . ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 10 October 2022, 12:57:58 UTC
0cf3088 Wenqi Li 30 September 2022, 07:00:15 UTC 5163 metatensor support for `OneOf` (#5217) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5163 ### Description enhance metatensor compatibility for `OneOf` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:57:58 UTC
4026c5e Nic Ma 30 September 2022, 05:46:53 UTC 5232 Enhance bundle page with more information (#5234) Fixes #5232 . ### Description According to user's feedback, this PR enhanced the MONAI bundle doc page to include tutorial examples and model-zoo info. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Nic Ma <nma@nvidia.com> 10 October 2022, 12:57:58 UTC
3d493ea Richard Brown 29 September 2022, 17:37:34 UTC protobuf should use PYEXE not pip (#5231) ### Description We should be using `PY_EXE` in runtests as opposed to raw `pip`. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> 10 October 2022, 12:57:58 UTC
a7e62d7 Richard Brown 29 September 2022, 12:16:57 UTC Visualisation classes to allow kwargs. combine GradCAM and ++ test files (#5224) ### Description Some users may have models that take adjoint information. This PR allows the adjoint information to be passed through the visualisation classes to the model via `**kwargs`. Also combined the test files of GradCAM and GradCAM++ as they were the same. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> 10 October 2022, 12:57:57 UTC
bacc6bb Yiheng Wang 29 September 2022, 10:36:47 UTC 4264 Add antialiasing option for `Resized` (#5223) Signed-off-by: Yiheng Wang <vennw@nvidia.com> Fixes #4264 . ### Description This PR adds the antialiasing option for `Resized` transform. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Yiheng Wang <vennw@nvidia.com> 10 October 2022, 12:57:57 UTC
e672b70 Wenqi Li 27 September 2022, 11:43:51 UTC 3844 flexible min/max_pixdim options for Spacing (#5212) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #3844 ### Description adding the flexibility for skipping the transform if the pixdim is in the specified range ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:57:57 UTC
c71df93 Wenqi Li 27 September 2022, 08:53:32 UTC 5211 5214 infer device from first item RandElastic, simplify `first_key()` default (#5213) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5211 Fixes #5214 ### Description - set device based on the first item: ```py device = self.rand_2d_elastic.device if device is None and isinstance(d[first_key], torch.Tensor): device = d[first_key].device # type: ignore self.rand_2d_elastic.set_device(device) ``` - simplied transform `first_key()` default to a tuple ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:57:57 UTC
b9f5dd8 Wenqi Li 26 September 2022, 11:26:27 UTC 5193 5204 import error msg/warnings (#5205) fixes #5193 fixes #5204 ### Description revise the import error messages and ignore a torchaudio warning. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:57:57 UTC
6a4dd92 YunLiu 26 September 2022, 09:33:35 UTC Fix typo in `RandScaleIntensityd` (#5210) Signed-off-by: KumoLiu <yunl@nvidia.com> Fixes #5209. ### Description Fix typo in `RandScaleIntensityd` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] In-line docstrings updated. Signed-off-by: KumoLiu <yunl@nvidia.com> 10 October 2022, 12:57:56 UTC
ed5fd2d Holger Roth 22 September 2022, 16:26:50 UTC update federated learning figure (#5194) Fixes #5031. ### Description Update federated learning figure. Using SVG format. Also removes from svg from gitignore. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 10 October 2022, 12:57:56 UTC
1c1815c YunLiu 21 September 2022, 15:18:06 UTC Add channel dim in `ComputeHoVerMaps` and `ComputeHoVerMapsd` (#5183) Signed-off-by: KumoLiu <yunl@nvidia.com> Fixes #5177. ### Description Add channel dim in `ComputeHoVerMaps` and `ComputeHoVerMapsd` to make it consistent with other transforms. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: KumoLiu <yunl@nvidia.com> Co-authored-by: Behrooz Hashemian <3968947+drbeh@users.noreply.github.com> 10 October 2022, 12:57:56 UTC
0a4b085 YunLiu 20 September 2022, 16:18:14 UTC Remove batch dim in `SobelGradients` and `SobelGradientsd` (#5182) Signed-off-by: KumoLiu <yunl@nvidia.com> Fixes #5176. ### Description Remove batch dim in `SobelGradients` and `SobelGradientsd` to make it consistent with other post transforms. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: KumoLiu <yunl@nvidia.com> 10 October 2022, 12:57:56 UTC
8de4af1 Wenqi Li 16 September 2022, 16:33:45 UTC 5090 releasing 1.0.0 (#5170) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5090 ### Description update version numbers ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 10 October 2022, 12:57:55 UTC
1700933 Wenqi Li 16 September 2022, 13:41:22 UTC Update URLs Signed-off-by: Wenqi Li <wenqil@nvidia.com> 16 September 2022, 13:42:25 UTC
f8ad6c6 Wenqi Li 16 September 2022, 13:08:45 UTC 5164 fixes wsireader test (#5165) Fixes #5164 ### Description fixes file path tests ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 16 September 2022, 13:08:45 UTC
70c0443 Wenqi Li 16 September 2022, 11:34:05 UTC 5090 5161 minor doc/env fixes (#5162) Fixes #5161 part of #5090 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 16 September 2022, 11:34:05 UTC
ca90628 Wenqi Li 15 September 2022, 21:08:36 UTC 5090 Update highlight and whats new (#5128) Signed-off-by: Wenqi Li <wenqil@nvidia.com> part of #5090 ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 15 September 2022, 21:08:36 UTC
d844caf Wenqi Li 15 September 2022, 13:37:50 UTC 5150 fixes integration error reading stdout visible devices (#5154) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5150 ### Description `python -m tests.utils` may print additional contents from 3rd party packages, only the last line for the stdout should be used ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 15 September 2022, 13:37:50 UTC
d763ca2 Mingxin Zheng 15 September 2022, 00:18:18 UTC update template hash (#5146) Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Fixes # . ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 15 September 2022, 00:18:18 UTC
57d4609 Abhijeet Parida 14 September 2022, 22:43:31 UTC fix(UNETR): access Bias term in SAB block (#5149) Fixes #5148 . ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: a-parida12 <abhijeet.parida@tum.de> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 14 September 2022, 22:43:31 UTC
a1e1af5 Wenqi Li 14 September 2022, 21:55:38 UTC 5090 update changelog for v1.0.0 (#5139) Signed-off-by: Wenqi Li <wenqil@nvidia.com> part of #5090 ### Description update the changelog please see also the backward compatibility guide: https://github.com/Project-MONAI/MONAI/blob/dev/CONTRIBUTING.md#backwards-compatibility ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 14 September 2022, 21:55:38 UTC
4a38e11 Mingxin Zheng 14 September 2022, 10:24:17 UTC json loader -> ConfigParser in template zip (#5143) Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Fixes datalist loader ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> 14 September 2022, 10:24:17 UTC
548160a Yiheng Wang 14 September 2022, 09:36:20 UTC 5140 Add update time information for bundle API (#5141) Signed-off-by: Yiheng Wang <vennw@nvidia.com> Fixes #5140 ### Description This PR is used to add `created_at` (the create time of a bundle) and `update_at` (the update time of a bundle) information in bundle API. It is helpful for showing the corresponding information in model zoo website. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Yiheng Wang <vennw@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 14 September 2022, 09:36:20 UTC
50c30c1 Mingxin Zheng 14 September 2022, 03:26:16 UTC Add Optuna and Improve Doc-strings for Auto3Dseg (#5137) ### Description Improve docstring and Optuna Integration(#5136 ) ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Signed-off-by: Mingxin Zheng <mingxin.zheng@philips.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Mingxin Zheng <mingxin.zheng@philips.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 14 September 2022, 03:26:16 UTC
02fb954 Wenqi Li 13 September 2022, 21:40:31 UTC 4456 optional import issue on top-level modules -- monai.handlers/monai.engines (#5132) Fixes #4456 ### Description make sure that if the top-level modules miss dependencies, the optional import error raises properly. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 13 September 2022, 21:40:31 UTC
d64c6d2 Richard Brown 13 September 2022, 12:37:21 UTC Keep n components (#5138) Fixes https://github.com/Project-MONAI/MONAI/issues/3809. ### Description Adds num_components argument. Defaults to 1 for backwards compatibility. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> 13 September 2022, 12:37:21 UTC
8700fee Wenqi Li 13 September 2022, 08:23:23 UTC review the transform.backend variable (#5126) Signed-off-by: Wenqi Li <wenqil@nvidia.com> part of https://github.com/Project-MONAI/MONAI/issues/4974 ### Description mostly documentation updates and non functional changes ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 13 September 2022, 08:23:23 UTC
53088c0 Behrooz Hashemian 13 September 2022, 06:40:00 UTC MetaTensor support in `ProbMapProducer` (#5117) Fixes #4954 ### Description This PR updates `ProbMapProducer` to works with `MetaTensors`. It will cause a backward incompatibility when used with the older version (non-MetaTensor versions) of `MaskedPatchWSIDataset` and `SlidingPatchWSIDataset`. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com> 13 September 2022, 06:40:00 UTC
af536ff Yiheng Wang 12 September 2022, 17:12:16 UTC 4948 Enhance bundle API for getting model zoo info (#4994) Signed-off-by: Yiheng Wang <vennw@nvidia.com> Fixes #4948 . ### Description This PR is used to enhance the bundle API, and enable to get: 1. a list of all bundles as well as their latest versions (by function `get_all_bundles_list`) 2. a bundle's latest version, and all existing verions (by function `get_bundle_versions`) 3. a bundle's information, include "id", "name", "size", "download_count", "browser_download_url". The information are achieved from github API directly (by function `get_bundle_info`) ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Yiheng Wang <vennw@nvidia.com> 12 September 2022, 17:12:16 UTC
5375a74 Wenqi Li 12 September 2022, 16:16:30 UTC 5127 fixes dtypes in randomized transforms (#5129) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5127 ### Description still does the dtype converting if self._do_transform is False ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 12 September 2022, 16:16:30 UTC
3908131 Mingxin Zheng 12 September 2022, 06:43:21 UTC Add Auto3Dseg AutoRunner (#5112) Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> ### Description The all-in-one minimal runner for auto3dseg pipeline. HPO is not included because PR is still WIP. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 12 September 2022, 06:43:21 UTC
d39ac50 Wenqi Li 11 September 2022, 09:27:15 UTC fixes typos and integration tests (#5121) Signed-off-by: Wenqi Li <wenqil@nvidia.com> ### Description run integration tests ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 11 September 2022, 09:27:15 UTC
7f7aff8 Mingxin Zheng 11 September 2022, 01:03:52 UTC Integrating HPO into Auto3Dseg (#5101) ### Description This is part of effort of Auto3D development. The goal of the PR is to address #4912. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Nic Ma <nma@nvidia.com> 11 September 2022, 01:03:52 UTC
c1b4dac Wenqi Li 10 September 2022, 17:34:10 UTC 5061 align corners and recompute_affine for spacing (#5075) Signed-off-by: Wenqi Li <wenqil@nvidia.com> Fixes #5061 ### Description computing output shape considering `align_corners`, recompute the output affine based on output shapes. a new `scale_extent` parameter is included to choose between the two resampling coordinate conventions. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 10 September 2022, 17:34:10 UTC
ea2502f Nic Ma 10 September 2022, 10:26:46 UTC Enhance BundleAlgo to support different template structures and download link (#5099) ### Description This PR enhanced the `BundleAlgo` base class to support different `sections` in the subclasses, for example DiNTS may need to save more config sections. And also enhanced the `BundleGen` to support other download link for the templates. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Nic Ma <nma@nvidia.com> Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> Co-authored-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> 10 September 2022, 10:26:46 UTC
81d2b30 Holger Roth 09 September 2022, 22:10:39 UTC 5118 monai algo multi configs support (#5119) Fixes #5118. ### Description Change config file parsing logic to support multiple files. Also separate the logic of parsing training and eval files and opted to not automatically merge both configs. The default will be to keep the same behavior as before. ``` config_train_filename = "configs/train.json" config_evaluate_filename = ["configs/train.json", "configs/evaluate.json"] ``` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> 09 September 2022, 22:10:39 UTC
59aeab0 Behrooz Hashemian 09 September 2022, 20:19:35 UTC MetaTensor for `GridPatch` and `RandGridPatch` (#5107) Fixes #4955 ### Description This PR makes `GridPatch`, `GridPatchd`, `RandGridPatch` and `RandGridPatchd` to create outputs as MetaTensors and return them as a single MetaTensor with `is_batch=True`. It also makes `get_default_affine()` a static method, similar to `get_default_meta()`, to be able to it in other places. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 09 September 2022, 20:19:35 UTC
15e15c6 Vishwesh 09 September 2022, 15:27:51 UTC Label Quality Assessment for Active Learning (#5065) Signed-off-by: Vishwesh Nath <vnath@nvidia.com> ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Vishwesh Nath <vnath@nvidia.com> 09 September 2022, 15:27:51 UTC
05de740 Wenqi Li 09 September 2022, 13:18:38 UTC adds a debugging flag for bundle parser (#5104) Signed-off-by: Wenqi Li <wenqil@nvidia.com> ### Description adds a `_debug_` keyword, so that when it's set to true, the program stops at the component init stage and enter the debug mode , usage: ```yaml inferer: _target_: SlidingWindowInferer _debug_: true roi_size: [96, 96, 96] sw_batch_size: 4 overlap: 0.5 ``` alternatively at the CLI set `MONAI_DEBUG_CONFIG=1`, for example: ```bash MONAI_DEBUG_CONFIG=1 python -m my_test_5 run --config_file=my_test_5.yaml ``` ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 09 September 2022, 13:18:38 UTC
e98226d Behrooz Hashemian 08 September 2022, 16:02:22 UTC Metadata in WSIReader and MetaTensor in WSIDatasets (#5077) Fixes #4956 and #4674 ### Description This PR implements micron-per-pixel (mpp) resolution calculation for `WSIReader` and all its backend, and adds `mpp` to the metadata to support the requested metadata from pathology WG. To be consistent with other image readers, `WSIReader` continue to return (image, metadata) pair instead of a MetaTensor (but it would be nice to reconsider it for all the image readers). It also updates WSIDatasets to return a MetaTensor and reference the required metadata via image.meta. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com> Co-authored-by: Nic Ma <nma@nvidia.com> 08 September 2022, 16:02:22 UTC
c71b0eb SACHIDANAND ALLE 07 September 2022, 23:00:34 UTC Fix deepgrow prepare data for 2D/3D (#5103) Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> Fixes # Fix data preparation for Deepgrow 2D/3D training ### Description Removing deprecated transform caused incorrect functionality for data-preparation step. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Sachidanand Alle <sachidanand.alle@gmail.com> 07 September 2022, 23:00:34 UTC
f4b6544 Mohammad Zalbagi Darestani 07 September 2022, 19:32:35 UTC Disable weight sharing for VarNet model (#5102) Signed-off-by: mersad95zd <m.zalbagi@gmail.com> Fixes # . ### Description Disable weight sharing in VarNet model. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: mersad95zd <m.zalbagi@gmail.com> 07 September 2022, 19:32:35 UTC
36200de Mohammad Zalbagi Darestani 07 September 2022, 14:55:49 UTC Edit varnet model (#5096) Signed-off-by: mersad95zd <m.zalbagi@gmail.com> Fixes #5095 ### Description Minor fixes to varnet model (its unit test). ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: mersad95zd <m.zalbagi@gmail.com> 07 September 2022, 14:55:49 UTC
f23077d Wenqi Li 07 September 2022, 11:59:38 UTC 4571 4616 remove deprecated api calls (#5089) fixes #4571 fixes #4616 fixes #5094 ### Description remove the deprecated calls ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 07 September 2022, 11:59:38 UTC
fb6d950 Yashika 07 September 2022, 06:40:55 UTC Implementing UNet++ (#5084) Fixes #896. ### Description Added Unet++. ### Status **Ready ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [ ] Non-breaking change (fix or new feature that would not break existing functionality). - [x] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Yashika Jain <yashikajain201@gmail.com> 07 September 2022, 06:40:55 UTC
91a58ed Abhijeet Parida 06 September 2022, 22:33:59 UTC Updated Contrastive Loss batch Size (#5093) Fixes #5070 . ### Description The batch size for the contrastive loss is estimated automatically ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: a-parida12 <abhijeet.parida@tum.de> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 06 September 2022, 22:33:59 UTC
0af5e18 YunLiu 06 September 2022, 17:12:36 UTC [WIP]Update auto3dseg docstring (#5083) Signed-off-by: KumoLiu <yunl@nvidia.com> Fixes # . ### Description Fix docstring in auto3dseg ### Status **Work in progress** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: KumoLiu <yunl@nvidia.com> Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> 06 September 2022, 17:12:36 UTC
658089b Behrooz Hashemian 06 September 2022, 16:06:10 UTC Remove Status from PR Template (#5092) ### Description This PR remove "Status" from PR template. The Status was very useful before GitHub introduced *Draft* PR. I believe right now it is redundant to have this and sometimes conflicting (e.g., Status Ready <> Draft PR), so I believe it is time to remove the "Status" from PR template. ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com> 06 September 2022, 16:06:10 UTC
4105299 Mingxin Zheng 06 September 2022, 14:57:58 UTC [Ready for review] Auto3D functional fixes in the BundleGen module (#5087) ### Description Part of the requested improvements #5085 Planned fixes - [x] fold number is not being updated in generate() - [x] put absolute paths in the bundle configs - [x] break the auto-generated auto_config into multiple files. ### Status WIP ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <18563433+mingxin-zheng@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Nic Ma <nma@nvidia.com> 06 September 2022, 14:57:58 UTC
8c4127b Eric Kerfoot 06 September 2022, 13:49:21 UTC Slight Fix For Type Conversion (#5091) Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> ### Description Using `view` to avoid copying doesn't actually work as intended in the type conversion to use `astype`. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 06 September 2022, 13:49:21 UTC
7fc5cf8 Eric Kerfoot 06 September 2022, 11:58:45 UTC Fix for Numpy Unsigned Array Conversion (#5082) Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> ### Description Numpy arrays with type uint16, uint32, and uint64 need to be converted to signed versions before conversion to Pytorch tensors. This is relevant because MR data is often stored in uint16 format. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> 06 September 2022, 11:58:45 UTC
b6016a9 Holger Roth 06 September 2022, 09:58:33 UTC Use Ignite's interrupt api in MonaiAlgo (#5071) Fixes #4554. Requires latest Ignite RC. Also improves ClientAlgo docstrings formatting. ### Description A few sentences describing the changes proposed in this pull request. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Holger Roth <hroth@nvidia.com> Signed-off-by: Nic Ma <nma@nvidia.com> Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: Nic Ma <nma@nvidia.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> 06 September 2022, 09:58:33 UTC
05856ef Wenqi Li 05 September 2022, 23:22:26 UTC 4909 remove deprecated args since v0.6 and v0.7 (#5055) Fixes #4909 ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Wenqi Li <wenqil@nvidia.com> 05 September 2022, 23:22:26 UTC
2ed44aa Eric Kerfoot 05 September 2022, 15:01:10 UTC Default prepare batch update (#5079) ### Description This allows `default_prepare_batch` to handle batches containing a single tensor or a pair of tensors. Normally if one uses array transforms you'll get an error saying the default batch function needs dictionaries so this will allow such transform sequences to be used without modification. ### Status **Work in progress** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> Co-authored-by: Wenqi Li <831580+wyli@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 05 September 2022, 15:01:10 UTC
b1aa40d Eric Kerfoot 05 September 2022, 07:17:57 UTC LogfileHandler (#5064) Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> ### Description Adds a handler for directing logging information to a file once an `Engine` object starts and then doing the cleanup when it completes. ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> 05 September 2022, 07:17:57 UTC
66df2b2 Mingxin Zheng 02 September 2022, 20:29:02 UTC Ensemble 5008 (#5012) Initial draft for #5008 . ### Description Ensemble models for Auto3Dseg and external algorithm ### Status **Ready** ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [ ] New tests added to cover the changes. - [ ] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [ ] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [ ] In-line docstrings updated. - [ ] Documentation updated, tested `make html` command in the `docs/` folder. Signed-off-by: Mingxin Zheng <mingxinz@nvidia.com> 02 September 2022, 20:29:02 UTC
back to top