GitLab

原因：
np.allclose(a, b, rtol)使用，计算误差是(a-b)的误差在(atol + rtol*b.abs())以内，但用例中b的值有0，误差就是atol了，atol默认是10的-8.
修改：
把atol根据用例改为传入的误差*10-3.

[Enhance] Add ConvModule.turn_on_fast_conv_bn_eval to reduce repetitive code and dynamically bind conv during forward (#2835)

[Feature] Add fast_conv_bn_eval option in ConvModule for fast validation and training in Eval mode (#2807)

* [Feature] Support Voxelization with cambricon MLU device (#2500)

* [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

* [Enhance] Optimize the performace of ms_deform_attn for MLU device (#2510)

* ms_opt

* ms_opt

* ms_opt

* ms_opt

* ms_opt

* [Feature] ms_deform_attn performance optimization

* [Feature] ms_deform_attn performance optimization

* [Feature] ms_deform_attn performance optimization

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

* [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.

* [Docs] Steps to compile mmcv-full on MLU machine (#2571)

* [Docs] Steps to compile mmcv-full on MLU machine

* [Docs] Adjust paragraph order

* Update docs/zh_cn/get_started/build.md
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update docs/zh_cn/get_started/build.md
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update docs/en/get_started/build.md
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* Update docs/en/get_started/build.md
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>

* [Docs] Modify the format

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

* [Fix] Fix tensor descriptor setting in MLU ball_query. (#2579)

* [Feature] Add MLU support for Sparse Convolution op (#2589)

* [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>

* [Enhancement] Replace the implementation of deform_roi_pool with mlu-ops (#2598)

* [Feature] Replace the implementation of deform_roi_pool with mlu-ops

* [Feature] Modify code

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

* [Enhancement] ms_deform_attn performance optimization (#2616)

* ms_opt_v2

* ms_opt_v2_1

* optimize MultiScaleDeformableAttention ops for MLU

* ms_opt_v2_1

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

* [Feature] ms_deform_attn performance optimization V2

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

* [Feature] Support NmsRotated with cambricon MLU backend (#2643)

* [Feature] Support NmsRotated with cambricon MLU backend

* [Feature] remove foolproofs in nms_rotated_mlu.cpp

* [Feature] fix lint in test_nms_rotated.py

* [Feature] fix kMLU not found in nms_rotated.cpp

* [Feature] modify mlu support in nms.py

* [Feature] modify nms_rotated support in ops.md

* [Feature] modify ops/nms.py

* [Enhance] Add a default value for MMCV_MLU_ARGS (#2688)

* add mlu_args

* add mlu_args

* Modify the code

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

* [Enhance] Ignore mlu-ops files (#2691)
Co-authored-by: budefei <budefei@cambricon.com>

---------
Co-authored-by: ZShaopeng <108382403+ZShaopeng@users.noreply.github.com>
Co-authored-by: BinZheng <38182684+Wickyzheng@users.noreply.github.com>
Co-authored-by: liuduanhui <103939338+DanieeelLiu@users.noreply.github.com>
Co-authored-by: budefei <budefei@cambricon.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: duzekun <108381389+duzekunKTH@users.noreply.github.com>
Co-authored-by: dongchengwei <dongchengwei@cambricon.com>
Co-authored-by: liuyuan1-v <125547457+liuyuan1-v@users.noreply.github.com>

* [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>

* fix

* fix lint

* [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>

* add ops bbox_overlaps

* format code

* Return the pytorch version

* Intermediate modification

* Solve problems in parameter passing

* revise bug

* "add test case"

* 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

* 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>

* Add voxelization op npu adaptor

* update

* update

* [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>

* fileio related interfaces should keep bc

* fix format

* update unit tests of transforms

* update format

* lazily infer client until calling get function of fileio

* 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

* bezier align

* add ut

* fix comment

* updata ut

* fix link and comment

* fix comment

* [Refactor] Use new interface of fileio

* update ut

* remove file_client_args

* add * before backend_args

* refine backend_args description

* 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>

* 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>

* [Feature] Support Iou3d with cambricon MLU backend

* [Feature] add double line

* [Feature] add line

* [Feature] Support RoiawarePool3d with cambricon MLU backend.

* [Feature] Support RoiawarePool3d with cambricon MLU backend.

* Fix three nn half inpt

* update test

* add stack sa model ops

* fix lint

* fix lint

* fix comments

* fix bug

* fix lint

* fix comments

* fix lint

* fix lint

* fix

* [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

* [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>

* 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