Commits · 06fa32853b923ba66965917d07bdb7497300fa20 · OpenDAS / MMCV

20 Mar, 2023 2 commits

[Feature] Add MLU support for Sparse Convolution op (#2589) · 06fa3285

duzekun authored Mar 20, 2023



* [Feature] Add sparse convolution MLU API

* [Feature] update cpp code style

* end-of-file

* delete libext.a

* code style

* update ops.md

---------
Co-authored-by: budefei <budefei@cambricon.com>

06fa3285

[Feature] Add Ascend support for RoIAlign op (#2638) · 01a0f53e

sherie authored Mar 20, 2023



* add roi_algin op

* add unit test

* update ops.md

* fix typo

---------

Co-authored-by: momo609 <963372609.qq.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

01a0f53e

03 Mar, 2023 1 commit
- [Feature] Add the support of voxelization op for ascend device (#2613) · 74598593
  liuhw authored Mar 03, 2023
```
* update

* update
```
  74598593
17 Feb, 2023 1 commit

[Enhancement] Support MultiScaleDeformableAttention with AMP (#2541) · 8e8ab226

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>

8e8ab226

06 Feb, 2023 2 commits
- [Feature] Add Ascend support for bbox_overlaps (#2580) · 5a61e534
  liuhw authored Feb 06, 2023
```
* Add support for Ascend devices with bbox_overlaps

* ...

* ...
```
  5a61e534
- [Feature] Add Ascend support for RoIPoolGrad op (#2569) · 615d2817
  xinliang123 authored Feb 06, 2023
```
* add roipoolgrad adapter

* amend
```
  615d2817
30 Jan, 2023 1 commit

[Feature] Add C++ implementation for bbox_overlaps (#2477) · 422816e4

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"

422816e4

28 Jan, 2023 1 commit

[Feature] Add support for Ascend devices with nms_rotated (#2550) · 54ed0ed8

ckirchhoff authored Jan 28, 2023

* [Feature]: add nms_rotated npu adaptater code

* [BugFix]: modify param in nms_rotated_npu.cpp

* [clean code]: nms_rotated_npu.cpp

* [clean code]: nms_rotated_npu.cpp

* [clean code]: nms_rotated_npu.cpp

* [clean code]: nms_rotated.cpp

* [Doc]: add nms_rotated op in supported op list at ops.md

* [Test]: add nms_rotated unit_test

* [Bug]: remove device parameter in test_batched_nms function

54ed0ed8

18 Jan, 2023 2 commits

[Feature] Support ball_query with cambricon MLU backend and mlu-ops library. (#2520) · dfb03806

liuduanhui authored Jan 18, 2023

* [Feature] Support ball_query with cambricon MLU backend and mlu-ops library.

* [Fix] update operator data layout setting.

* [Fix] add cxx compile option to avoid symbol conflict.

* [Fix] fix lint errors.

* [Fix] update ops.md with info of ball_query support by MLU backend.

* [Feature] Fix typo.

* [Fix] Remove print.

* [Fix] get mlu-ops from MMCV_MLU_OPS_PATH env.

* [Fix] update MMCV_MLU_OPS_PATH check logic.

* [Fix] update error info when failed to download mlu-ops.

* [Fix] check mlu-ops version matching info in mmcv.

* [Fix] revise wrong filename.

* [Fix] remove f.close and re.

dfb03806

[Feature] Add support for Ascend devices with gather_points (#2555) · 84f60c17
zcc-zjut authored Jan 18, 2023

84f60c17

13 Jan, 2023 2 commits
- [Enhance] Add AMP support for MLU_DCNv2 (#2548) · 71ee2a61
  mengpenghui authored Jan 13, 2023
  
  71ee2a61
- [Feature] Add MLU support for DCN (#2540) · c310d28c
  mengpenghui authored Jan 13, 2023
  
  c310d28c
12 Jan, 2023 1 commit
- [Feature] Add Ascend support for RoIPool op (#2483) · 2810718a
  sherie authored Jan 12, 2023
```
Co-authored-by: wangxiaoxin_sherie <wangxiaoxin7@huawei.com>
```
  2810718a
10 Jan, 2023 1 commit

[Feature] Support Voxelization with cambricon MLU device (#2500) · 48ea88ab

ZShaopeng authored Jan 10, 2023

* [Feature] Support hard_voxelize with cambricon MLU backend

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

* [Feature](bangc-ops): add voxelization op

48ea88ab

06 Jan, 2023 1 commit
- [Feature] Support PSAMask op for Ascend device (#2487) · 73856344
  DaGaiBa authored Jan 06, 2023
  
  73856344
28 Dec, 2022 1 commit
- [Fix] Fix skip_layer for RF-Next (#2489) · 935ba78b
  Zhongyu Li authored Dec 28, 2022
```
* judge skip_layer by fullname

* lint

* skip_layer first

* update unit test
```
  935ba78b
14 Dec, 2022 1 commit

[Feature] Add NPU adapter for Deformable RoIPool (#2481) · 46eb9ec5

jayggh authored Dec 14, 2022

* add npu adapter for deformroipool

* cleancode

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

46eb9ec5

13 Dec, 2022 1 commit

[Feature] Add FusedBiasLeakyRelu npu adapter (#2474) · 4c51afce

jayggh authored Dec 13, 2022



* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* clean code

* fix autocast bugs on npu (#2273)

fix autocast bugs on npu (#2273)

* code format

* code format

* code format

* bug fix

* pytorch_npu_helper.hpp clean code

* Npu dev (#2306)

* fix autocast bugs on npu
* using scatter_kwargs in mmcv.device.scatter_gather

* raise ImportError when compile with npu

* add npu test case (#2307)

* add npu test case

* Update focal_loss.py

* add comment

* clean lint

* update dtype assert

* update DDP forward and comment

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

* sigmoidfocalloss npu adapter bug fix

* BugFix: modify softmaxFocalLoss adapter

* BugFix: remove equal sign in the code

* add npu install information in README

* add modulatedDeformConv npu adapter

* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* add modulatedDeformConv npu adapter

* merge master branch 20221103

* Add masked_ Conv2d operator in NPU

* add nms_npu

* fix bug

* fix code check

* fix code check

* fix code check

* Masked_conv2d NPU

* Masked_conv2d NPU

* Masked_conv2d NPU

* remove npu-install-info in README.md

* annotate the clang-format in pre-commit-config-zh-ch.yaml

* Clean code: fix the clean code problem in masked_conv2d and modulated_deform_conv

* Create fused_bias_leakyrelu_npu.cpp

Add NPU adapter for fused_bias_leaky_relu operator

* Update fused_bias_leakyrelu_npu.cpp

* Update fused_bias_leakyrelu_npu.cpp

* Update ops.md

* Update ops.md

* Update fused_bias_leakyrelu_npu.cpp

* Update fused_bias_leakyrelu_npu.cpp

* Update test_fused_bias_leakyrelu.py

* Update fused_bias_leakyrelu.py

* Update test_fused_bias_leakyrelu.py

* Update fused_bias_leakyrelu.py

* Update test_fused_bias_leakyrelu.py

* Update ops.md

* amend for CI

* bugfix

* amend ops.md

* Update test_fused_bias_leakyrelu.py

* clean code

* bugfix

* clean code

* Update fused_bias_leakyrelu_npu.cpp

* Update fused_bias_leakyrelu_npu.cpp
Co-authored-by: wangjiangben <wangjiangben_hw@126.com>
Co-authored-by: ckirchhoff <515629648@qq.com>
Co-authored-by: wangjiangben-hw <111729245+wangjiangben-hw@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: zcc-zjut <zcczxy2019@163.com>
Co-authored-by: wangxiaoxin_sherie <wangxiaoxin7@huawei.com>
Co-authored-by: momo609 <963372609@qq.com>

4c51afce

11 Dec, 2022 1 commit
- [Fix] Fix ut caused by the new version of packaging (#2482) · 4e67e481
  Zaida Zhou authored Dec 11, 2022
  
  4e67e481
04 Dec, 2022 1 commit

[Feature] Support modulated_deform_conv with cambricon MLU backend (#2411) · 49d89175

mengpenghui authored Dec 04, 2022



* [Feature] Support modulated_deform_conv with cambricon MLU backend

* fix error of torch_mlu

* modify with commit suggestion

* Update modulated_deform_conv.py

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

49d89175

28 Nov, 2022 1 commit

[Enhance] Add conf_path in PetrelBackend (#2459) · c1712ee2

SUNYC authored Nov 28, 2022

* feat: add conf_path in PetrelBackend

* fix: add conf_path in MockPetrelClient

* fix: adjust parameters order

c1712ee2

22 Nov, 2022 1 commit

[Feature] Support receptive field search of CNN models (#2056) · 6e3827d0

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>

6e3827d0

16 Nov, 2022 1 commit

[Feature] Support MultiScaleDeformableAttn with cambricon MLU backend (#2396) · 12442667

ZShaopeng authored Nov 16, 2022



* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support MsDeformAttnForward with cambricon MLU backend

* [Feature] Support ms with cambricon MLU backend

* [Feature] Support msdeformattn_1104 with cambricon MLU backend

* [Feature] Support ms with cambricon MLU backend

* [Feature] Support MsDeformAttn_1108 with cambricon MLU backend

* [Feature] Support MsDeformAttn_1108 with cambricon MLU backend

* [Feature] Support MsDeformAttn_1108 with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* Revert "[Feature] Support MsDeformAttn with cambricon MLU backend"

This reverts commit 27963cccc86d240852a40a2c1510147a3e9f269f.

* [Feature] Support MsdeformAttn with cambricon MLU backend

* [Feature] Support MsDeformAttn with cambricon MLU backend

* [Feature] Support MsdeformAttn with cambricon MLU backend
Co-authored-by: zhangshaopeng <wicky-zheng@outlook.com>
Co-authored-by: wicky-zheng <root@notebook-mmcv-290m8-torch1-6-y0yv66-notebook-0.notebook-mmcv-290m8-torch1-6-y0yv66.ns-ad8b689a0ecd41fcb4469c803dcd539d.svc.cluster.local>

12442667

15 Nov, 2022 1 commit

[Feature] Support masked_conv in Ascend device (#2387) · de6b0021

ckirchhoff authored Nov 15, 2022



* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* clean code

* fix autocast bugs on npu (#2273)

fix autocast bugs on npu (#2273)

* code format

* code format

* code format

* bug fix

* pytorch_npu_helper.hpp clean code

* Npu dev (#2306)

* fix autocast bugs on npu
* using scatter_kwargs in mmcv.device.scatter_gather

* raise ImportError when compile with npu

* add npu test case (#2307)

* add npu test case

* Update focal_loss.py

* add comment

* clean lint

* update dtype assert

* update DDP forward and comment

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

* sigmoidfocalloss npu adapter bug fix

* BugFix: modify softmaxFocalLoss adapter

* BugFix: remove equal sign in the code

* add npu install information in README

* add modulatedDeformConv npu adapter

* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* add modulatedDeformConv npu adapter

* merge master branch 20221103

* Add masked_ Conv2d operator in NPU

* add nms_npu

* fix bug

* fix code check

* fix code check

* fix code check

* Masked_conv2d NPU

* Masked_conv2d NPU

* Masked_conv2d NPU

* remove npu-install-info in README.md

* annotate the clang-format in pre-commit-config-zh-ch.yaml

* Clean code: fix the clean code problem in masked_conv2d and modulated_deform_conv
Co-authored-by: wangjiangben <wangjiangben_hw@126.com>
Co-authored-by: wangjiangben-hw <111729245+wangjiangben-hw@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: zcc-zjut <zcczxy2019@163.com>
Co-authored-by: wangxiaoxin_sherie <wangxiaoxin7@huawei.com>
Co-authored-by: momo609 <963372609@qq.com>

de6b0021

08 Nov, 2022 1 commit
- [Fix] Create Tensor with new_* method to support amp (#2389) · 6254ebef
  q.yao authored Nov 08, 2022
  
  6254ebef
03 Nov, 2022 1 commit

[Feature] Support RoIAwarePool3d with cambricon MLU backend (#2359) · b622fb2e

Zhang authored Nov 03, 2022

* [Feature] Support RoiawarePool3d with cambricon MLU backend.

* [Feature] Support RoiawarePool3d with cambricon MLU backend.

b622fb2e

28 Oct, 2022 2 commits

[Features] Add stack ball query and stack group points ops (#2292) · 93fe4829

VVsssssk authored Oct 28, 2022

* add stack sa model ops

* fix lint

* fix lint

* fix comments

* fix bug

* fix lint

* fix comments

* fix lint

* fix lint

* fix

93fe4829

[Feature] Add box_iou_quadri & nms_quadri (#2277) · a4f304a5

Yue Zhou authored Oct 13, 2022

* update

* update

* fix link

* fix bug

* update nms_quadri

* fix lint

* Update test_nms_quadri.py

* Update box_iou_quadri.py

* fix bug

* Update test_nms_quadri.py

* Update box_iou_rotated_utils.hpp

* Update box_iou_quadri.py

* Update mmcv/ops/nms.py

a4f304a5

24 Oct, 2022 3 commits

[Enhancement] Add a new argument define_metric in wandb hook (#2237) · 9709ff3f

takuoko authored Oct 25, 2022



* wandb define_metric

* add test and some fix based on mmengine PR

* fix test

* add summary warnings

* Update mmcv/runner/hooks/logger/wandb.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update mmcv/runner/hooks/logger/wandb.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

9709ff3f

[Feature] Support Iou3d with cambricon MLU backend (#2339) · 7fd7058a
cathyzhang222 authored Oct 24, 2022
```
* [Feature] Support Iou3d with cambricon MLU backend

* [Feature] add double line

* [Feature] add line
```
7fd7058a
[Fix] Fix three nn op can not accept half tensor (#2348) · 6cf9ac05
q.yao authored Oct 24, 2022
```
* Fix three nn half inpt

* update test
```
6cf9ac05

12 Oct, 2022 1 commit

[Enhancement] Add ability to pass logger instance to frameworks (#2317) · e417035f

Ivan Shcheklein authored Oct 11, 2022



* Add ability to pass logger instance to frameworks

* refine docstring

* Update mmcv/runner/hooks/logger/dvclive.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

e417035f

11 Oct, 2022 2 commits

[Feature] Support PrRoI op for Parrots (#2280) · dd5b415d

CokeDong authored Oct 11, 2022

* Support parrots extension for op PrRoI

* Fix lint

* Fix cpp lint

* Fix testcase failure by false requires_grad in self-defined autograd Funtion

* Fix issues

* Fix flake8

* Fix isort

* Adaption for typechecking for PrRoIPoolFunction

* Fix lint

* Support only float32

* bugfix

dd5b415d

[Refactor] Refactor the nms3d op to support MLU (#2296) · c001e2fc

q.yao authored Oct 11, 2022

* update iou3d

* fix parrot

* update to device

* replace count_nonzero with fill

* update build.yml

c001e2fc

08 Oct, 2022 1 commit
- Upgrade pre commit hooks (#2321) · b6a7fd98
  Zaida Zhou authored Oct 08, 2022
```
* Upgrade the versions of pre-commit hooks

* update the versions of zh-cn.yaml
```
  b6a7fd98
30 Sep, 2022 1 commit

[Feature] Support training on NPU device (#2262) · a5db5f66

wangjiangben-hw authored Sep 30, 2022



* init npu

* add npu extension and focal loss adapter

* clean code

* clean code

* clean code

* clean code

* fix autocast bugs on npu (#2273)

fix autocast bugs on npu (#2273)

* code format

* code format

* code format

* bug fix

* pytorch_npu_helper.hpp clean code

* Npu dev (#2306)

* fix autocast bugs on npu
* using scatter_kwargs in mmcv.device.scatter_gather

* raise ImportError when compile with npu

* add npu test case (#2307)

* add npu test case

* Update focal_loss.py

* add comment

* clean lint

* update dtype assert

* update DDP forward and comment

* fix bug
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: ckirchhoff <515629648@qq.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

a5db5f66

29 Sep, 2022 1 commit

[Enhancement] Support SiLU with torch < 1.7.0 (#2278) · afff3886

takuoko authored Sep 29, 2022



* support silu torch<1.7.0

* fix test

* fix test

* fix inplace

* fix inplace

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

afff3886

13 Sep, 2022 1 commit
- [Feature] Register a new activatation layer SiLU to ACTIVATION_LAYERS (#2256) · 55c51e17
  takuoko authored Sep 13, 2022
  
  55c51e17
08 Sep, 2022 1 commit

[Feature] Support RoipointPool3d with cambricon MLU backend (#2247) · 83bedf5a

ZShaopeng authored Sep 08, 2022

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

* [Feature] Support RoipointPool3d with cambricon MLU backend

83bedf5a

28 Aug, 2022 1 commit

[Feature] Support DeformRoiPool with cambricon MLU backend (#2137) · e843d73f

bdf authored Aug 28, 2022



* [Feature] Support DeformRoiPool with cambricon MLU backend

* [Fix] Remove use of std library

* [Fix] Correct the error information

* [Refactor] Refactor test deform_roi_pool code

* [Fix] Fix judgment error

* [Fix] Modify the large tensor check
Co-authored-by: budefei <budefei@cambricon.com>

e843d73f