Commits · 1db3967e860569c1501af4bff6c0964dec402289 · OpenDAS / MMCV

25 Mar, 2023 3 commits

Fix lint (#2702) · 1db3967e
Zaida Zhou authored Mar 26, 2023

1db3967e

[Fix] Enhance the compatibility of training stylegan 2 (#2694) · 5b0cdccc

Mashiro authored Mar 26, 2023



* [Fix] Enhance the compatibility of training stylegan 2

* Fix unit test in PyTorch 2.0

* Apply suggestions from code review

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

5b0cdccc

[Fix] Replace torch/extension.h with torch/types.h to fix compilation error on Windows (#2698) · aa250d0a

q.yao authored Mar 25, 2023



* replace extension to types

* update setup

* Update setup.py

* Update setup.py

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

aa250d0a

24 Mar, 2023 1 commit
- [Fix] Fix torch2.0 dcn/mdcn symbolic (#2695) · a6d7dde7
  q.yao authored Mar 24, 2023
```
* fix

* fix lint
```
  a6d7dde7
21 Mar, 2023 2 commits
- Do not build pre-built pakcages for torch1.6 and 1.7 on macOS platform (#2678) · 5a45fac9
  Zaida Zhou authored Mar 21, 2023
```
* build macos

* fix python version

* fix python version

* Do not build pre-built pakcages for torch1.6 and 1.7 in macOS platform
```
  5a45fac9
- Bump version to v2.0.0 (#2675) · 6a5cd177
  Zaida Zhou authored Mar 21, 2023
  
  6a5cd177
20 Mar, 2023 6 commits

Refine rfsearch and fix a typo · c4588297
Mashiro authored Jan 17, 2023

c4588297
[Fix] Fix a typo in the docstring of MSDeformAttn (#2599) · 1f9e5b57
Hakjin Lee authored Feb 13, 2023

1f9e5b57
Fix the paper link error in the docstring (#2618) · b248efa5
BainOuO authored Feb 27, 2023

b248efa5

[Enhancement] Support MultiScaleDeformableAttention with AMP (#2541) · 4ad79591

Hakjin Lee authored Feb 17, 2023



* [Enhance] Support FP16 for MSDeformAttn

* [Fix] Data type mismatch

* Update mmcv/ops/multi_scale_deform_attn.py

* Add UT

Author:    nijkah <nijkah@gmail.com>

* Add cuda available condition

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

4ad79591

[Feature] Add C++ implementation for bbox_overlaps (#2477) · 0e14ce2c

enemy1205 authored Jan 31, 2023

* add ops bbox_overlaps

* format code

* Return the pytorch version

* Intermediate modification

* Solve problems in parameter passing

* revise bug

* "add test case"

0e14ce2c

[Feature] Support receptive field search of CNN models (#2056) · bc10b5f0

Shanghua Gao authored Nov 22, 2022



* support rfsearch

* add labs for rfsearch

* format

* format

* add docstring and type hints

* clean code
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* rm unused func

* update code

* update code

* update code

* update  details

* fix details

* support asymmetric kernel

* support asymmetric kernel

* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Apply suggestions from code review

* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Apply suggestions from code review

* add unit tests for rfsearch

* set device for Conv2dRFSearchOp

* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* remove unused function search_estimate_only

* move unit tests

* Update tests/test_cnn/test_rfsearch/test_operator.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update mmcv/cnn/rfsearch/operator.py
Co-authored-by: Yue Zhou <592267829@qq.com>

* change logger

* Update mmcv/cnn/rfsearch/operator.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: lzyhha <819814373@qq.com>
Co-authored-by: Zhongyu Li <44114862+lzyhha@users.noreply.github.com>
Co-authored-by: Yue Zhou <592267829@qq.com>

[Fix] Fix skip_layer for RF-Next (#2489)

* judge skip_layer by fullname

* lint

* skip_layer first

* update unit test

bc10b5f0

19 Mar, 2023 1 commit
- [Fix] Skip filtered_lrelu ut when cuda is less than 10.2 (#2677) · e7adffb9
  Zaida Zhou authored Mar 19, 2023
  
  e7adffb9
17 Mar, 2023 3 commits
- [Fix] nms_rotated_npu accepts angle parameter (#2674) · d31b2212
  NoCakeAnyMore authored Mar 17, 2023
  
  d31b2212
- [Fix] Skip fused_lrelu op when gcc is less than 6.0 or cuda is less than 10.2 (#2671) · 03ea1c9d
  q.yao authored Mar 17, 2023
```
* disable filtered_lrelu_op

* fix lint

* add cuda version check

* warning if disable
```
  03ea1c9d
- Build macOS pre-built packages for PyTorch2.0 in CI (#2668) · 91ed30dd
  Zaida Zhou authored Mar 17, 2023
```
* Add support for pytorch2.0

* minor fix

* update
```
  91ed30dd
15 Mar, 2023 1 commit
- [Fix] Prevent divide-by-zero error on Ascend device for bbox_overlaps (#2646) · 3ad02efd
  liuhw authored Mar 15, 2023
  
  3ad02efd
13 Mar, 2023 1 commit

[Feature] Add Ops of StyleGAN3 (#2290) · 869dbf1b

Yifei Yang authored Mar 13, 2023



* add bias_act

* support bias_act

* support filtered_lrelu

* support filtered_lrelu and upfirdn2d

* support conv2d_gradfix and fix filtered_lrelu

* fix lint

* fix lint

* fix c++ lint

* fix part comments

* fix lint

* rm redundant header

* fix upgrade pip

* fix as comment

* fix c++ lint

* fix ci

* fix-ut

* fix as comments

* add grad check

* remove redundant template

* Update mmcv/ops/bias_act.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* add typehint

* fix as comment:

* complete type hints

* fix lint

* add test for conv_gradfix

* add test for conv_gradfix

* fix lint

* modify licenses and ops.md

* add zh op md

* add torch version policy for conv2d_gradfix

* fix lint

* fix as comments

* rename impl

* rm redudant function and add ut

* fix as comment

* fix lint

* fix lint

* fix as comments

* fix lint

* fix ut

* fix as comment

* fix as comment

* fix as comment

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

869dbf1b

03 Mar, 2023 1 commit
- [Feature] Add the support of voxelization op for ascend device (#2614) · 0fb07d0e
  liuhw authored Mar 03, 2023
```
* Add voxelization op npu adaptor

* update

* update
```
  0fb07d0e
17 Feb, 2023 2 commits
- [Fix] Call operator __half explicit (#2608) · 998e4597
  q.yao authored Feb 18, 2023
  
  998e4597
- Register Compose to TRANSFORMS (#2600) · a019d2a3
  Mashiro authored Feb 17, 2023
  
  a019d2a3
13 Feb, 2023 1 commit

[Feature] Add support of some ops for Ascend device (#2594) · 834f94db

ckirchhoff authored Feb 13, 2023



* [Feature]: add supports of gather_points, nms_rotated, bbox_overlaps for Ascend device

* Apply suggestions from code review

---------
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

834f94db

08 Feb, 2023 1 commit
- [Docs] Add api references in docs (#2587) · 8e2b2bf3
  Qian Zhao authored Feb 08, 2023
  
  8e2b2bf3
31 Jan, 2023 1 commit
- Use official isort (#2575) · c84d52cd
  tripleMu authored Jan 31, 2023
  
  c84d52cd
29 Jan, 2023 1 commit
- [Fix] Upgrade the version of isort to fix lint error (#2567) · 6cae40a4
  tripleMu authored Jan 29, 2023
  
  6cae40a4
18 Jan, 2023 1 commit
- Bump version to v2.0.0rc4 (#2559) · eb57b3bb
  Zaida Zhou authored Jan 18, 2023
  
  eb57b3bb
17 Jan, 2023 1 commit

Zaida Zhou authored Jan 17, 2023

* fileio related interfaces should keep bc

* fix format

* update unit tests of transforms

* update format

* lazily infer client until calling get function of fileio

009cfe60

13 Jan, 2023 1 commit

[Feature] Pick npu ops from master to 2.x (#2501) · 34bdf448

ckirchhoff authored Jan 13, 2023

* merge npu ops from master to 2.x

* BugFix: fix merge bugs

* {[Feature]: add psamask, roipool to 2.x, and fix the SigmoidFocalLoss assert condition

* merge conflicts in ops.md

* [fix]: fix merge bug

34bdf448

10 Jan, 2023 2 commits
- [Feature] Add BezierAlign CUDA op (#2393) · 7156604e
  liukuikun authored Jan 10, 2023
```
* bezier align

* add ut

* fix comment

* updata ut

* fix link and comment

* fix comment
```
  7156604e
- Update parrots image (#2538) · 78fdf178
  CokeDong authored Jan 10, 2023
```
* Update image for 2.x

* Update install cmd for 2.x
```
  78fdf178
08 Jan, 2023 1 commit

[Fix] Fix CI failed due to the version of protobuf (#2529) · 16155078

Mashiro authored Jan 08, 2023



* [Fix] Fix CI failed caused by protobuf

* minor refine

* test minimum_version_gpu

* test minimum_version_gpu

* test minimum_version_gpu

* fix ci

* remove protobuf from requirements
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

16155078

06 Jan, 2023 2 commits
- [Fix] _flip_keypoint of RandomFlip returns a wrong result (#2527) · fadd915c
  Zaida Zhou authored Jan 06, 2023
  
  fadd915c
- Deprecate the support for python3.6 (#2525) · 4ae327f4
  Mashiro authored Jan 06, 2023
```
* [Fix] Adjust the minimum supported version of Python to 3.6

* refine the docs
```
  4ae327f4
27 Dec, 2022 1 commit

[Refactor] Use the new interface of fileio from mmengine (#2468) · a3cb0685

Zaida Zhou authored Dec 28, 2022

* [Refactor] Use new interface of fileio

* update ut

* remove file_client_args

* add * before backend_args

* refine backend_args description

a3cb0685

20 Dec, 2022 1 commit
- [Fix] Fix the version of Windows OS to 2019 (#2503) · 32cc2f7c
  q.yao authored Dec 20, 2022
  
  32cc2f7c
11 Dec, 2022 2 commits

[Feature] Support LayerScale in FFN (#2451) · d510b8b1

takuoko authored Dec 11, 2022



* add layer scale

* add layer scale

* add layer scale

* Update mmcv/cnn/bricks/transformer.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update mmcv/cnn/bricks/transformer.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* add layer scale

* move LayerScale

* add layer_scale_init_value

* add typehint

* fix for tensor with any dim

* fix layer scale rule

* fix layer scale rule

* fix test

* add docs
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

d510b8b1

[Enhancement] Support value_proj_ratio in MultiScaleDeformableAttention (#2452) · 43360703

takuoko authored Dec 11, 2022



* add ratio in ms_deform_attn_

* add ratio in ms_deform_attn

* Update mmcv/ops/multi_scale_deform_attn.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update tests/test_ops/test_ms_deformable_attn.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* add ratio in ms_deform_attn

* add ratio in ms_deform_attn

* add ratio in ms_deform_attn

* add ratio in ms_deform_attn

* add ratio in ms_deform_attn

* add ratio in ms_deform_attn
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

43360703

06 Dec, 2022 3 commits
- [Docs] Update qq group link (#2454) · fb39e1e5
  vansin authored Dec 06, 2022
```
* [Doc] update qq group link

* [Doc] update qq group link

* [Doc] update zhihu link

* [Doc] update the wechat qrcode link
```
  fb39e1e5
- [Docs] Add convention for the order of data transforms (#2442) · fd11b874
  liukuikun authored Dec 06, 2022
  
  fd11b874
- [Fix] Fix optimizer 'ValueError' when using PReLU activation (#2444) · 6e818309
  Kei-Chi Tse authored Dec 06, 2022
```
* fix optimizer ValueError when using PReLU activation.

* fix lint error
```
  6e818309