Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

merge master #333

Merged
merged 273 commits into from
Dec 23, 2021
Merged

merge master #333

merged 273 commits into from
Dec 23, 2021

Conversation

Nic-Ma
Copy link
Owner

@Nic-Ma Nic-Ma commented Dec 23, 2021

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

Nic-Ma and others added 30 commits September 16, 2021 03:55
@Nic-Ma
[DLMED] fix float64 bug (#2961)
fb2c2e9 
Signed-off-by: Nic Ma <nma@nvidia.com>
@ahatamiz
add multi-modal (vision + language) transformers (#2962)
3b6f479 
* add multimodal transformers

Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
@rijobro
Torch: map_binary_to_indices, map_classes_to_indices, `correct_cr…
71ebd91 
…op_centers`, `generate_pos_neg_label_crop_centers`, `generate_label_classes_crop_centers` (#2958)

torch map_binary_to_indices, map_classes_to_indices, correct_crop_centers, generate_pos_neg_label_crop_centers, generate_label_classes_crop_centers
@drbeh
cuCIM Transform (#2932)
38403ed 
* Implement CuCIM wrapper transfrom

Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com>
@rijobro
torch SpatialCrop, SpatialCropd (#2963)
0c39281 
Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
@drbeh
Update with cupy.ndarray (#2965)
43a4342 
* Update with cupy.ndarray

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

* Change to use has_cp

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

* Change the format

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

* Fix a bug

Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com>
@ericspod
Fix for Jupyter plotting (#2964)
46e594f 
* Fix for Jupyter plotting

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Fix for Jupyter plotting

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Fix for Jupyter plotting

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>
@wyli
fixes tutorial issue 352 (#2968)
dc3e263 
* fixes tutorial issue 352

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

* simplified

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
2231 Enhance tensor transforms (#2966)
ecbb03b 
* [DLMED] enhance tensor transforms

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

* [DLMED] fix tests

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

* [DLMED] fix mypy

Signed-off-by: Nic Ma <nma@nvidia.com>
@rijobro
Torch RandCropByPosNegLabel, RandCropByPosNegLabeld, `RandCropByL…
e2e2d08 
…abelClasses`, `RandCropByLabelClassesd` (#2967)

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
@wyli
enhance affinegrid to use torch backend (#2969)
ee202fa 
* enhance affinegrid to use torch backend

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

* style fixes

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

* codeformat fixes

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

* backend affien grid

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

* device support

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

* less lookup

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

* create grid with torch backend

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

* fixes tests

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

* default to torch create grid

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

* fixes unit test

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

* randaffine with create grid

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

* create_grid backend change for spatial transforms

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

* create control grid tensor

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

* enhance spatial, and crop xforms

  - Update test_rand_deform_grid.py
  - center_scale_crop
  - center_spatial_crop
  - rand_scale_crop
  - rand_spatial_crop
  - rand_spatial_crop_samples

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

* fixes invert

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

* tensor resize, unit test fixes

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@drbeh
Add make the name of wsi reader lowercase (#2973)
e2e5e31 
Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com>
@ahatamiz
update multimodal doc and model names (Transchex) (#2979)
731bad8 
* update multimodal doc and model names (Transchex)

Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
@wyli
2914 remove the deprecated API for v0.7 (#2981)
f786957 
* remove deprecated

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

* min-test list

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

* preserves tests from tests/test_handler_transform_inverter.py

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
2985 - enhance nightly test (#2986)
b791ed2 
* enhance nightly test

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

* print after the test for information

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@neuronflow @monai-bot
dimension check for pretrained model weights (#2984)
f31b55f 
* dimension check for pretrained model weights

This PR implements a dimension check, before trying to load pre-trained model weights.

Signed-off-by: neuronflow <zournyque@gmail.com>

* [MONAI] python code formatting

Signed-off-by: monai-bot <monai.miccai2019@gmail.com>
Signed-off-by: neuronflow <zournyque@gmail.com>

* multi line split error

Signed-off-by: neuronflow <zournyque@gmail.com>

Co-authored-by: monai-bot <monai.miccai2019@gmail.com>
@deepsource-autofix @wyli
Refactor unnecessary else / elif when if block has a return s…
790fc8f 
…tatement (#2996)

* Refactor unnecessary `else` / `elif` when `if` block has a `return` statement

* Remove unnecessary lambda expression (#2997)

Co-authored-by: deepsource-autofix[bot] <62050782+deepsource-autofix[bot]@users.noreply.github.com>

* type fixes

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

* remove repeated init

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

* fixes import, unused vars

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>
@Nic-Ma @monai-bot
3000 Support not copy in CacheDataset (#3001)
d3d1743 
* [DLMED] add copy option

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

* [DLMED] enhance test

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>
@wyli
3002 - compatibility with torch 1.9.1 (#3003)
ed2d12c 
* test 1.9.1

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

* temp tests

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

* Revert "temp tests"

This reverts commit 1f27a63.

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
Fix cucim dep compatibility (#3006)
dfe8528 
* fixes cucim compatibility

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

* simplified import

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
update cucim dep (#3007)
b3406ae 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
[DLMED] fix CI test (#3008)
eed14df 
Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3009 Update highlights web page (#3013)
46bf30d 
* [DLMED] update highlights

Signed-off-by: Nic Ma <nma@nvidia.com>
@wyli
2914 release note, and what's new for v0.7 (#2992)
64fa255 
* release note v0.7

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

* adds whatsnew 07

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
delaying the removal (#3015)
bfa054b 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
update preview version tag (#3016)
f06de43 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
Enhance 0.7 README doc (#3017)
aa4eb5d 
* [DLMED] update README

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

* [DLMED] update what's new

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

* [DLMED] use whatsnew link

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3020 Enhance what's new for transfomer networks (#3019)
a9cd2d8 
* [DLMED] add more doc

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

* [DLMED] edit change log

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

* [DLMED] add command to get transform backend

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

* [DLMED] enhance the doc

Signed-off-by: Nic Ma <nma@nvidia.com>
@rijobro
Torch GaussianSmooth, RandGaussianSmooth, GaussianSharpen, `Ran…
453a9c0 
…dGaussianSharpen` (#2971)

Torch `GaussianSmooth`, `RandGaussianSmooth`, `GaussianSharpen`, `RandGaussianSharpen`
@Borda
apply pyupgrade (#3026)
a477905 
* apply pyupgrade

Signed-off-by: Jirka <jirka.borovec@seznam.cz>

* exclude monai/_version.py

Signed-off-by: Jirka <jirka.borovec@seznam.cz>
wyli and others added 29 commits December 9, 2021 14:53
@wyli
revise MILModel docstring (#3459)
82576e7 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
deprecate reduction (#3464)
4b5ad0b 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma @monai-bot
3444 Add DatasetFunc (#3456)
5b36d02 
* [DLMED] add dataset generator

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

* [DLMED] add DatasetGenerator

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

* [DLMED] update according to comments

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

* [MONAI] python code formatting

Signed-off-by: monai-bot <monai.miccai2019@gmail.com>

* [DLMED] fix wrong test

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

* [DLMED] simplify according to comments

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

* [DLMED] remove return

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

* [DLMED] update rtol for CI

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

Co-authored-by: monai-bot <monai.miccai2019@gmail.com>
@Nic-Ma
Add missing components to API doc (#3468)
89f0bd4 
* [DLMED] add missing docs

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

* [DLMED] add missing components

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

* [DLMED] fix test

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma @monai-bot
3466 3467 Add channel_wise and correct doc-string (#3469)
d386213 
* [DLMED] add channel-wise

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

* [DLMED] update according to comments

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

* [DLMED] fix typo

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

* [DLMED] skip test if before 1.7

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>
@Nic-Ma
[DLMED] remove cls (#3475)
a4c1300 
Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
Add Iteration base class (#3472)
360c52f 
* [DLMED] add Iteration base class

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>
@yiheng-wang-nv
fix link error (#3488)
cb70e13 
Signed-off-by: Yiheng Wang <vennw@nvidia.com>
@Nic-Ma
3465 Support string as dtype (#3478)
9ef0070 
* [DLMED] support string dtype

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

* [DLMED] fix typo

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

* [DLMED] enhance dtype in ToCupy

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
[DLMED] update to 0.4.7 (#3483)
7a66f18 
Signed-off-by: Nic Ma <nma@nvidia.com>
@drbeh
Improve NVTX Range Naming (#3484)
f6648a3 
* Update to not include number for the name of the first range

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

* Update CuCIM and TorchVision wrappers to include name

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

* Update nvtx range to append undelying class for wrapper tranforms

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

* Add new test cases to cover changes

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

* Update cucim and torchvision check

Signed-off-by: Behrooz <3968947+drbeh@users.noreply.github.com>
@Nic-Ma
3471 3491 Add example images for intensity transforms (#3494)
9927691 
* [DLMED] add missing images

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

* [DLMED] fix 3471

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

* [DLMED] fix AsDiscrete

Signed-off-by: Nic Ma <nma@nvidia.com>
@ebrahimebrahim
Make bending energy loss invariant to resolution (#3493)
88d91d6 
* make bending energy loss invariant to resolution

fixes #3485

Signed-off-by: Ebrahim Ebrahim <ebrahim.ebrahim@kitware.com>

* set BendingEnergyLoss default normalize to False

Maybe it's more important that the default behavior match usage of the
term "bending energy" elsewhere, rather than that it be the most
convenient behavior.

Signed-off-by: Ebrahim Ebrahim <ebrahim.ebrahim@kitware.com>
@wyli
Removes redundant casting -- ensure tuple (#3495)
3761ee0 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
3498 Correct kwargs arg for convert_to_torchscript (#3499)
a255648 
* [DLMED] correct kwargs

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

* [DLMED] fix grammar

Signed-off-by: Nic Ma <nma@nvidia.com>
@wyli
update tests with 1.10.1 (#3500)
531c276 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
3501 Add dict version SavitzkyGolaySmoothd (#3502)
d663d78 
* [DLMED] add SavitzkyGolaySmoothd

Signed-off-by: Nic Ma <nma@nvidia.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>
@wyli
remove file (#3507)
d2861a2 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
avoid 60.0.0 (#3514)
29779d1 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
[DLMED] add 6 new transform images (#3512)
c9d38f0 
Signed-off-by: Nic Ma <nma@nvidia.com>
@wyli
support of reversed indexing (#3508)
1d3a9d7 
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@ericspod @pre-commit-ci
@monai-bot @Nic-Ma
Adding Torchscript utility functions (#3138)
9734478 
* Adding Torchscript utility functions

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [MONAI] python code formatting

Signed-off-by: monai-bot <monai.miccai2019@gmail.com>

* Adding Torchscript utility functions

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Added test for extra files

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Update

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Update

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Updates

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Updates

Signed-off-by: Eric Kerfoot <eric.kerfoot@kcl.ac.uk>

* Updates

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>
Co-authored-by: monai-bot <monai.miccai2019@gmail.com>
Co-authored-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3517 Refine AddCoordinateChannels transform (#3524)
8e2ade5 
* [DLMED] change to utility transforms

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

* [DLMED] enhance args

Signed-off-by: Nic Ma <nma@nvidia.com>
@wyli
3521 Copyright header update (#3522)
1516ca7 
* adds missing item

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

* update the contributing guide

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

* update copyright headers

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
3521 - adds a util to check the licence info (#3523)
299a0d1 
* util to check the licence info

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

* update flags

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

* update based on comments

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@Nic-Ma
3350 Remove PyTorch 1.5.x related logic and mark versions for all new…
58ded72 
… APIs (#3526)

* [DLMED] clarify old APIs

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

* [DLMED] update according to comments

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3533 Update PyTorch docker to 21.12 (#3534)
08f9bac 
* [DLMED] update to 21.12

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

* [DLMED] update according to comments

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

* [DLMED] add PyTorch 1.9 test

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3531 Add args to subclass of CacheDataset (#3532)
9caa1d0 
* [DLMED] add missing args

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

* [DLMED] update according to comments

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

* [DLMED] update progress arg

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma
3525 Fix invertible issue in OneOf compose (#3530)
6767959 
* [DLMED] fix oneof

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

* [DLMED] add more unit tests

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

* [DLMED] update index

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

* [DLMED] update according to comments

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

* Revert "[DLMED] update according to comments"

This reverts commit c6c3a35.

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

* Revert "[DLMED] update index"

This reverts commit 649a7c5.

Signed-off-by: Nic Ma <nma@nvidia.com>
@Nic-Ma Nic-Ma merged commit a6d5127 into Nic-Ma:3539-remove-decollate-warning Dec 23, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.