merge master by Nic-Ma · Pull Request #63 · Nic-Ma/MONAI

Nic-Ma · 2021-04-02T11:50:36Z

Fixes # .

Description

A few sentences describing the changes proposed in this pull request.

Status

Ready/Work in progress/Hold

Types of changes

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 --codeformat --coverage.
Quick tests passed locally by running ./runtests.sh --quick.
In-line docstrings updated.
Documentation updated, tested make html command in the docs/ folder.

* update openmp flag Signed-off-by: Wenqi Li <wenqil@nvidia.com> * improves boundtype docs Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update setup.py Signed-off-by: Wenqi Li <wenqil@nvidia.com> * input validation 1d Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes typos Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes typos Signed-off-by: Wenqi Li <wenqil@nvidia.com> * merge upstream changes Signed-off-by: Wenqi Li <wenqil@nvidia.com> * tests enums Signed-off-by: Wenqi Li <wenqil@nvidia.com> * init. test grid pull Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update Signed-off-by: Wenqi Li <wenqil@nvidia.com> * test grid_pull Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes min test Signed-off-by: Wenqi Li <wenqil@nvidia.com> * adds device tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * bwd tests Signed-off-by: Wenqi Li <wenqil@nvidia.com>

move transforms out of compose file. this is backwards compatible.

* pad_collation Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> * increase number of test cases to ensure required testing errors Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> * determinism in setUp Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> * pad collate for list of lists Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> * code format Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com> * allow padding options Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

decollate batch

enhance random range parameters If element `i` is iterable, then `uniform[-rotate_range[i][0], rotate_range[i][1])` will be used to generate the rotation parameter for the ith dimension. If not, `uniform[-rotate_range[i], rotate_range[i])` will be used. This can be altered on a per-dimension basis. E.g., `((0,3), 1, ...)`: for dim0, rotation will be in range `[0, 3]`, and for dim1 `[-1, 1]` will be used. Setting a single value will use `[-x, x]` for dim0 and nothing for the remaining dimensions. Backwards compatibility is ensured because the old behaviour used to do `uniform[-rotate_range[i], rotate_range[i])`, and this PR just adds the possibility to do `uniform[-rotate_range[i][0], rotate_range[i][1])`.

* Fixing issues preventing loss functions from being compatible with Torchscript Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> * Updates Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> * Updates Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> * Updates Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> * Adding conditional skip to Torchscript tests Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

* [DLMED] fix length > 1024 issue in string list all gather Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] add more test Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: Yiheng Wang <68361391+yiheng-wang-nv@users.noreply.github.com>

* DeleteChannel array, dictionary, tests Signed-off-by: Leo Tam <leot@nvidia.com> * formatting Signed-off-by: Leo Tam <leot@nvidia.com> * DeleteChannel array, dictionary, tests Signed-off-by: Leo Tam <leot@nvidia.com> * Register in transform init Signed-off-by: Leo Tam <leot@nvidia.com> * clean comment Signed-off-by: Leo Tam <leot@nvidia.com> * Dict init Signed-off-by: Leo Tam <leot@nvidia.com> * Register D and Dict Signed-off-by: Leo Tam <leot@nvidia.com> * Style fix Signed-off-by: Leo Tam <leot@nvidia.com> * Safety cast Signed-off-by: Leo Tam <leot@nvidia.com> * Changinging names from DeleteChannel to RemoveRepeatedChannel Signed-off-by: Leo Tam <leot@nvidia.com> * Lint fixes Signed-off-by: Leo Tam <leot@nvidia.com> * Test import fix, autofix again Signed-off-by: Leo Tam <leot@nvidia.com>

Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>

* update distcall Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update final closing Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>

* Add ToPIL transformation Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add ToPILd, ToPILD, ToPILDict Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove has_pil Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Include ToPIL, ToPILd, ToPILD, and ToPILDict Also include ToNumpyD, ToNumpyDict, TorchVisionD, and TorchVisionDict Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix a typing issue Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix PIL optional import Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittests for ToPIL and ToPILD Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix formatting Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix formatting Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add PILImage.Image as the input for ToNumpy and ToTensor Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix type checking issue for PIL.Image.Image Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Change PILImage_fromarray to lower case Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

add RandomizableTransform

* Add more tests to test_deepgrow_dataset Signed-off-by: YuanTingHsieh <yuantinghsieh@gmail.com>

* Add inference transforms Signed-off-by: YuanTingHsieh <yuantinghsieh@gmail.com> * Remove unused import Signed-off-by: YuanTingHsieh <yuantinghsieh@gmail.com> * Fix review comments Signed-off-by: YuanTingHsieh <yuantinghsieh@gmail.com> Co-authored-by: SACHIDANAND ALLE <sachidanand.alle@gmail.com>

* [DLMED] add RandAxisFlip transforms Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> * [DLMED] fix flake8 issues Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

fix big endianness problem for dictionary reading. Also allow dictionary image_only

* [DLMED] add AutoAdjustChannel transform Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] add dict version transform Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> * [DLMED] fix doc-build issue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to Wenqi's comments Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update doc-strings Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

Allow missing keys

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* Update load pretrain for densenet Signed-off-by: Yiheng Wang <vennw@nvidia.com> * Fix isort issue Signed-off-by: Yiheng Wang <vennw@nvidia.com>

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Signed-off-by: Yiheng Wang <vennw@nvidia.com>

* [DLMED] add suqeeze to handler Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com>

* fixes #1285 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * adds test Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* fixes #1685 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * add temp test Signed-off-by: Wenqi Li <wenqil@nvidia.com> * adds docstring Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes dist sampler Signed-off-by: Wenqi Li <wenqil@nvidia.com> * remove temp tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes type hint issue Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* fixes data type in switching Signed-off-by: Wenqi Li <wenqil@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

* Implement CuImageReader and OpenSlideReader Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittests for CuImageReader Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittests for OpenSlideReader Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Sort imports Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add correct boundaries Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add test cases for reading patches on a grid for CuImage Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add patch whole slide imaging dataset for pathology Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add test case for read patches for OpenSlide Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * flake8 and few minor changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * black Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * flake8 Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add kwargs to CuImageReader and OpenSlideReader's read method Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Change the type hint from np.dtype to DTypeLike Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix a bug Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Implement WSIReader and unittests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Minor updates Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix few typing issues Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Revert datasets Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add shape property to openslide image object Reverse size to be compatible with output size (hxw) Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add untittest for loading the whole image Reverse the size accroding to the WSIReader Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update the whole image size Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove optional size Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove optional dtype Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove _get_spatial_shape return type Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Reverse the orders of dimensions of `location` to be compatible with image shape Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Change test cases to use smaller image and revese location's dimensions Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Replace the test TIFF and some upgrades Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update dependencies for OpenSlide Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update unittests for OpenSlide and CuImage Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix openslide dependency Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix doc dependencies Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Minor changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Few variable name changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add EnsureChannelFirst Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add metadata to WSIReader Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Signed-off-by: Nic Ma <nma@nvidia.com>

* fix lr finder

* [DLMED] add MapLabelValue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] add unit tests Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] add missing doc-string Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com>

* Add unittests for SmartCachePatchWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Turn off shuffle for SmartCachePatchWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* fixes #1848 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * temp tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * Revert "temp tests" This reverts commit 563e7ea. Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Signed-off-by: Nic Ma <nma@nvidia.com>

Allowing the choice of epoch and iteration interval. Signed-off-by: Petru-Daniel Tudosiu <petru.daniel@tudosiu.com>

* [DLMED] enhance list_collate Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> * [DLMED] update based on comments Co-authored-by: Wenqi Li <wenqil@nvidia.com> Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com>

Signed-off-by: Nic Ma <nma@nvidia.com>

* [DLMED] add slicing support in datasets Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] add unit tests Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> * [DLMED] fix typo Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update doc-strings and typehints Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] fix flake8 issue Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

* download_if_not_exist Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update cuimage reader tests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update openslide reader tests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update the file path to be relative to the test file Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update patch wsi dataset tests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update smartcache patch wsi dataset tests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Revert "download_if_not_exist" This reverts commit a4c65f3. Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update with download_url Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * [MONAI] python code formatting

* Implement random bias field transform Signed-off-by: Yiheng Wang <vennw@nvidia.com>

* Fixing error in saving non-pytorch-variable parameters for backwards pass Signed-off-by: chaliebudd <charles.budd@kcl.ac.uk> * Adding unit tests to check bilateral filter backwards runs Signed-off-by: chaliebudd <charles.budd@kcl.ac.uk> * fixing typo introduced by merge Signed-off-by: chaliebudd <charles.budd@kcl.ac.uk> * code reformatting Signed-off-by: chaliebudd <charles.budd@kcl.ac.uk>

* fixes warping Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes types Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update based on comments Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes warnings in setup.cfg, config, deprecated assertexecption Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* Remove assert statement from non-test files * Remove redundant `None` default * Use `is` to compare type of objects * Refactor unnecessary `else` / `elif` when `if` block has a `raise` statement * Refactor unnecessary `else` / `elif` when `if` block has a `return` statement * runtests.sh --autofix Signed-off-by: Wenqi Li <wenqil@nvidia.com> * autofix/7d8e8b86-113e-4a5a-8d0d-c621aab7b5f2 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * fixes assert types Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com>

Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

* Implement MaskedInferenceWSIDataset for pathology inference Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update pathology init Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update docs Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove last elemnt of cum_num_patches Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittest with multiple cases for MaskedInferenceWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * sort imports in init Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove list dataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove try/except and add type hint Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Convert the sample output to a list Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove some type hints Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove prints Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update based on commnets Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update patch_size Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update unittests Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add more type hints Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

* remove unused in_channels in LNCC Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update integration tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * extending warp options Signed-off-by: Wenqi Li <wenqil@nvidia.com>

* [DLMED] enhance brats transform Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

* Fix stdshift type error Signed-off-by: Yiheng Wang <vennw@nvidia.com> * Add dtype testcases Signed-off-by: Yiheng Wang <vennw@nvidia.com>

* Implement ProbMapGenerator handler Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update doc and init Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Sort init imports Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittest for ProbMapGenerator Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Ignore if ignite is not available Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update Engine import Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Exclude from min-test Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Address all the comments Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix file path and dtype Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

* Implement MaskedInferenceWSIDataset for pathology inference Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update pathology init Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update docs Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove last elemnt of cum_num_patches Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add unittest with multiple cases for MaskedInferenceWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * sort imports in init Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove list dataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove try/except and add type hint Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Convert the sample output to a list Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove some type hints Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Implement FROC calcualtion for pathology Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update ProbNMS doctring Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update docs and change namings Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix a bug and minor changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Minor changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Fix docstring formatting Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Add a type hint Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Implement unittests for EvaluateTumorFROC Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Ignore type for np.amax Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove space Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Ignore type for range instead of np.amax Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Skip test if PIL is not available Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update docstring Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Skip ground truth generating if PIL is not available Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update unittest Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove print Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Rename TumorFROC and add few type hints Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Rename evaluators to metrics Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Remove non-relevant files Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Rename to LesionFROC and minor changes Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Update test Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

* Rename the prob map producer unittest to match the module Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Change probs_map to prob_map Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Prepend image_inference_outputs with temp to be ignored Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Signed-off-by: Yiheng Wang <vennw@nvidia.com>

* followup of #1878, fixes tests, remove json loading Signed-off-by: Wenqi Li <wenqil@nvidia.com> * Update test ordinal numbers Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> Co-authored-by: Behrooz <3968947+behxyz@users.noreply.github.com>

* clip variance to be >= 0 Signed-off-by: kate-sann5100 <yiwen.li@st-annes.ox.ac.uk> * max for torch1.6 Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com>

* update to use pytorch2103 Signed-off-by: Wenqi Li <wenqil@nvidia.com>

wyli and others added 30 commits February 24, 2021 15:02

move transforms out of compose file (#1623)

3a1c459

move transforms out of compose file. this is backwards compatible.

decollate batch (#1624)

69d9fcc

decollate batch

[DLMED] add progress arg (#1647)

c68d25e

Signed-off-by: Nic Ma <nma@nvidia.com> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>

1650-update distcall (#1652)

5875ae6

* update distcall Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update final closing Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com>

Randomizable constructor (#1639)

1df6352

add RandomizableTransform

Add more tests to test_deepgrow_dataset (#1654)

4b8819a

* Add more tests to test_deepgrow_dataset Signed-off-by: YuanTingHsieh <yuantinghsieh@gmail.com>

allow dictionary image only and test endianness (#1669)

20e17b2

fix big endianness problem for dictionary reading. Also allow dictionary image_only

[1662] Allow missing keys (#1676)

421c0a9

Allow missing keys

nifti saver squeeze dims (#1680)

27543c8

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

improve gradcam doc (#1682)

b533afd

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

fixes integration tests (#1683)

7cfb529

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Update load pretrain for densenet (#1684)

4bd9cf3

* Update load pretrain for densenet Signed-off-by: Yiheng Wang <vennw@nvidia.com> * Fix isort issue Signed-off-by: Yiheng Wang <vennw@nvidia.com>

revise the dtype according to the discussion (#1671)

8cc200f

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Fix senet pretrained weights issue (#1689)

ac9f953

Signed-off-by: Yiheng Wang <vennw@nvidia.com>

1680 Add squeeze SegmentationSaver handler (#1686)

380f042

* [DLMED] add suqeeze to handler Signed-off-by: Nic Ma <nma@nvidia.com> * [DLMED] update according to comments Signed-off-by: Nic Ma <nma@nvidia.com>

1285 adds module list (#1690)

114faf0

* fixes #1285 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * adds test Signed-off-by: Wenqi Li <wenqil@nvidia.com>

fixes data type in switching (#1694)

75b5772

* fixes data type in switching Signed-off-by: Wenqi Li <wenqil@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

[DLMED] add WSIReader to LoadImage (#1695)

232e8a5

Signed-off-by: Nic Ma <nma@nvidia.com>

rijobro and others added 29 commits March 26, 2021 19:53

[1859] fix lr finder (#1865)

32e6b12

* fix lr finder

Update SmartCachePatchWSIDataset and add unittests (#1853)

c157fb8

* Add unittests for SmartCachePatchWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> * Turn off shuffle for SmartCachePatchWSIDataset Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

adds-bicubic-option (#1850)

61a2a21

Signed-off-by: Wenqi Li <wenqil@nvidia.com>

1848 - testing with pytorch 1.8.1 (#1856)

76beeb2

* fixes #1848 Signed-off-by: Wenqi Li <wenqil@nvidia.com> * temp tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * Revert "temp tests" This reverts commit 563e7ea. Signed-off-by: Wenqi Li <wenqil@nvidia.com>

[DLMED] support single item (#1884)

a1f938a

Signed-off-by: Nic Ma <nma@nvidia.com>

Epoch/Iteration interval (#1870)

9f6ceeb

Allowing the choice of epoch and iteration interval. Signed-off-by: Petru-Daniel Tudosiu <petru.daniel@tudosiu.com>

[DLMED] add data_root_dir arg (#1890)

f3ccbac

Signed-off-by: Nic Ma <nma@nvidia.com>

Implement random bias field transform (#1886)

f0c9c18

* Implement random bias field transform Signed-off-by: Yiheng Wang <vennw@nvidia.com>

Update WSIReader for CuCIM (#1876)

1612ec3

Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

remove unused in_channels in LNCC (#1903)

ca8481f

* remove unused in_channels in LNCC Signed-off-by: Wenqi Li <wenqil@nvidia.com> * update integration tests Signed-off-by: Wenqi Li <wenqil@nvidia.com> * extending warp options Signed-off-by: Wenqi Li <wenqil@nvidia.com>

1905 Enhance the brats transform (#1906)

b1d45ee

* [DLMED] enhance brats transform Signed-off-by: Nic Ma <nma@nvidia.com> * [MONAI] python code formatting Signed-off-by: monai-bot <monai.miccai2019@gmail.com> Co-authored-by: monai-bot <monai.miccai2019@gmail.com>

Fix stdshift type error (#1907)

2a7e1ce

* Fix stdshift type error Signed-off-by: Yiheng Wang <vennw@nvidia.com> * Add dtype testcases Signed-off-by: Yiheng Wang <vennw@nvidia.com>

Update CuCIM (#1909)

613f25e

Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Update pathology unittests (#1910)

5fec791

Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com>

Implement dice_focal loss (#1914)

ba127a2

Signed-off-by: Yiheng Wang <vennw@nvidia.com>

followup of #1878 (#1913)

debc561

* followup of #1878, fixes tests, remove json loading Signed-off-by: Wenqi Li <wenqil@nvidia.com> * Update test ordinal numbers Signed-off-by: Behrooz <3968947+behxyz@users.noreply.github.com> Co-authored-by: Behrooz <3968947+behxyz@users.noreply.github.com>

1868-fix-potential-inf-in-lncc-loss (#1915)

32e540f

* clip variance to be >= 0 Signed-off-by: kate-sann5100 <yiwen.li@st-annes.ox.ac.uk> * max for torch1.6 Signed-off-by: Wenqi Li <wenqil@nvidia.com> Co-authored-by: Wenqi Li <wenqil@nvidia.com>

1919 - test pt 2103 (#1920)

4bd26f9

* update to use pytorch2103 Signed-off-by: Wenqi Li <wenqil@nvidia.com>

Nic-Ma merged commit f60772b into Nic-Ma:1900-save-batch Apr 2, 2021

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

merge master#63

merge master#63
Nic-Ma merged 135 commits into
Nic-Ma:1900-save-batchfrom
Project-MONAI:master

Nic-Ma commented Apr 2, 2021

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

11 participants

Conversation

Nic-Ma commented Apr 2, 2021

Description

Status

Types of changes

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

11 participants