merge master #37
Merged
merge master #37
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* 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: 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>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
8 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes # .
Description
A few sentences describing the changes proposed in this pull request.
Status
Ready/Work in progress/Hold
Types of changes
./runtests.sh --codeformat --coverage../runtests.sh --quick.make htmlcommand in thedocs/folder.