944a53f9d9
[Docs] Add currently npu supported ops in ops.md ( #2420 )
2022-11-17 14:16:36 +08:00
eda3c57ea1
Add torch1.13 checking in CI ( #2405 )
...
* Add torch1.13 checking in CI
* swith to python3.10
* fix
* cancel comments
2022-11-17 11:28:52 +08:00
12442667ff
[Feature] Support MultiScaleDeformableAttn with cambricon MLU backend ( #2396 )
...
* [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>
2022-11-16 14:08:04 +08:00
057b25ae88
[Docs] Add code style guide ( #2406 )
...
* [Docs] Add code style guide
* add typing and mypy links
* fix format
2022-11-15 11:28:16 +08:00
de6b0021af
[Feature] Support masked_conv in Ascend device ( #2387 )
...
* 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>
2022-11-15 10:23:17 +08:00
89253699da
[Fix] Fix DCN TensorRT plugin ( #2408 )
2022-11-14 19:09:10 +08:00
652b1bf207
[Feature] Support NMS with cambricon MLU590 backend ( #2401 )
...
* [Feature] Support Nms with cambricon MLU590 backend
support 590 for nms
* add blank
2022-11-11 16:44:44 +08:00
3efe957f40
Update supported pytorch versions ( #2382 )
...
* Update supported pytorch versions
* update
* fix
2022-11-11 15:40:50 +08:00
6254ebef8d
[Fix] Create Tensor with new_* method to support amp ( #2389 )
2022-11-08 15:54:34 +08:00
b622fb2e29
[Feature] Support RoIAwarePool3d with cambricon MLU backend ( #2359 )
...
* [Feature] Support RoiawarePool3d with cambricon MLU backend.
* [Feature] Support RoiawarePool3d with cambricon MLU backend.
2022-11-03 11:13:34 +08:00
270c293c9b
Bump version to v1.7.0 ( #2362 )
...
* Bump version to v1.7.0
* remove deprecated message
2022-11-01 17:33:54 +08:00
ff8e0c8a3c
[Docs] Add maintenance plan and print deprecated message ( #2357 )
...
* [Docs] Add maintenance plan
* Update maintenance plan
* Update compatibility.md
* Update README
* resolve comments
* Update README
* Add warning info
* update
* fix typo
2022-11-01 17:02:41 +08:00
e2c9fc450e
[Docs] Add steps to install mmcv-full on NPU machine ( #2363 )
...
* Add steps to install mmcv-full on NPU machine
Co-authored-by: wangxiaoxin_sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangjiangben-hw <111729245+wangjiangben-hw@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-10-31 23:44:07 +08:00
14e8e4904b
[Fix] Fix set_device bug when using multi-machine multi-device ( #2370 )
2022-10-31 22:56:48 +08:00
b51341909b
Build torch1.13 pre-built package for macOS in CI ( #2366 )
...
* Add torch1.13 for macOS in CI
* update
* fix typo
* Update
2022-10-31 14:28:30 +08:00
93fe4829f7
[Features] Add stack ball query and stack group points ops ( #2292 )
...
* add stack sa model ops
* fix lint
* fix lint
* fix comments
* fix bug
* fix lint
* fix comments
* fix lint
* fix lint
* fix
2022-10-28 16:53:33 +08:00
a4f304a5f5
[Feature] Add box_iou_quadri & nms_quadri ( #2277 )
...
* 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
2022-10-28 16:53:33 +08:00
f48975b2e3
[Fix] Fix MPS ops for torch1.12+ ( #2302 )
2022-10-28 16:53:33 +08:00
1eef4f5a4e
[Docs] Update README and fix typo in docs ( #2358 )
2022-10-26 17:31:48 +08:00
3c35bab67c
[Fix] Fix the potential NaN bug in calc_square_dist() ( #2356 )
2022-10-26 14:06:28 +08:00
9709ff3f8c
[Enhancement] Add a new argument define_metric in wandb hook ( #2237 )
...
* 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>
2022-10-24 23:13:07 +08:00
ff18904721
[Fix] Fix Correlation op ( #2274 )
...
* fix correlation
* fix lint
2022-10-24 17:08:13 +08:00
7fd7058a9c
[Feature] Support Iou3d with cambricon MLU backend ( #2339 )
...
* [Feature] Support Iou3d with cambricon MLU backend
* [Feature] add double line
* [Feature] add line
2022-10-24 15:58:58 +08:00
6d9e4a9b78
Build macOS wheel in Github Action ( #2311 )
...
* Bump version to
* update
2022-10-24 12:38:40 +08:00
6cf9ac0507
[Fix] Fix three nn op can not accept half tensor ( #2348 )
...
* Fix three nn half inpt
* update test
2022-10-24 11:15:21 +08:00
04ec054e6b
[Fix] Fix the bug of uninitialized prarmeter ( #2345 )
...
* [Fix] Fix the bug of uninitialized prarmeter
* refactor code for lint
Co-authored-by: budefei <budefei@cambricon.com>
2022-10-20 20:12:15 +08:00
be684eeb4c
[Feature] Add getJobLimitCapability interface and use it in nms ( #2337 )
...
Co-authored-by: budefei <budefei@cambricon.com>
2022-10-18 14:24:27 +08:00
bd1da5ab47
[Docs] Refine README and installation documentations ( #1977 )
...
* [Docs] Refine README
* refine table
* minor refinement
* refine
* refine
* add version info
* add version info
* update version info
* refine
* refine
* add module links in docs/en/introduction
* update docs/en
* fix typo
* update docs/en
* add version.json in zh_cn
* minor refinement
* update version.json
* update Dockerfile
* minor fix
* update installation of macOS
* resolve comments
2022-10-17 17:10:03 +08:00
e417035f5d
[Enhancement] Add ability to pass logger instance to frameworks ( #2317 )
...
* 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>
2022-10-12 12:09:53 +08:00
dd5b415d2a
[Feature] Support PrRoI op for Parrots ( #2280 )
...
* 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
2022-10-11 15:21:00 +08:00
c001e2fcba
[Refactor] Refactor the nms3d op to support MLU ( #2296 )
...
* update iou3d
* fix parrot
* update to device
* replace count_nonzero with fill
* update build.yml
2022-10-11 10:24:46 +08:00
b1711db048
[Refactor] Adapt mlu code to cntoolkit3.0.1 ( #2248 )
...
* [Refactor] Adapt mlu code to cntoolkit3.0.1
* [Refactor] Modify the code style
Co-authored-by: budefei <budefei@cambricon.com>
Co-authored-by: budefei <budefei@cambricon>
2022-10-10 22:40:41 +08:00
8e844d1b5c
Fix warning of CUDA ops ( #2324 )
2022-10-10 14:07:40 +08:00
b6a7fd98e4
Upgrade pre commit hooks ( #2321 )
...
* Upgrade the versions of pre-commit hooks
* update the versions of zh-cn.yaml
2022-10-08 11:48:44 +08:00
a5db5f6682
[Feature] Support training on NPU device ( #2262 )
...
* 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>
2022-09-30 21:05:37 +08:00
92504176bc
Update onnx registry ( #2294 )
...
* update onnx registry
* move import
2022-09-29 22:12:08 +08:00
afff388692
[Enhancement] Support SiLU with torch < 1.7.0 ( #2278 )
...
* 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>
2022-09-29 15:19:41 +08:00
847612dfff
Bump version to v1.6.2 ( #2285 )
2022-09-26 19:02:26 +08:00
629ef89c0d
Pick commits from 2.x branch ( #2284 )
...
* [Fix] Fix the calculation error of out_w in MaskedConv2dFunction (#2264 )
* [Fix] Fix two intergers can not use / operator in torch1.6
* should not use kernel_h when calculates out_w
* [Docs] Fix some mistakes in data_process.md (#2283 )
* correction
* correction en docs
Co-authored-by: yxzhao <33384732+yxzhao2022@users.noreply.github.com>
2022-09-25 23:26:04 +08:00
3b9b9054bf
[Enhancement] Add support of TorchVision's Model Registration API on MMCV ( #2246 )
...
* Add support of TorchVision's Model Registration API.
* fix linter
* formatting with yapf
2022-09-14 16:41:35 +08:00
25f533b916
Fix spconv clang-format ( #2260 )
2022-09-14 11:01:09 +08:00
55c51e1734
[Feature] Register a new activatation layer SiLU to ACTIVATION_LAYERS ( #2256 )
2022-09-13 22:38:23 +08:00
2046a394a2
[Fix] Use ROCm backened within the PyTorch framework ( #1918 )
...
* modified code for using ROCm backened within the PyTorch framework
* added hip runtime header
* flake8 linting fix
2022-09-13 15:43:48 +08:00
2fb2b91aed
Add type hints for mmcv/image ( #2089 )
...
* Fix typehint
* minor fix
* minor fix
* minor fix
Co-authored-by: zhouzaida <zhouzaida@163.com>
2022-09-12 17:16:55 +08:00
3a311e85ae
[Docs] Add zhihu articles ( #2157 )
...
* [Docs] Add zhihu articles
* add OpenMMLabCourse link
* fix typo
2022-09-11 22:21:52 +08:00
83bedf5a2b
[Feature] Support RoipointPool3d with cambricon MLU backend ( #2247 )
...
* [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
2022-09-08 17:19:12 +08:00
e08b80911f
No restritions on onnx versions ( #2251 )
2022-09-08 15:44:27 +08:00
7f09a983c3
[Docs] Fix the example error in registry.md ( #2243 )
...
the lack of colon(:)
2022-09-02 11:37:45 +08:00
e843d73fc7
[Feature] Support DeformRoiPool with cambricon MLU backend ( #2137 )
...
* [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>
2022-08-28 22:37:28 +08:00
505b5771eb
[Fix] cast the type of mask to enable training with amp ( #2220 )
2022-08-28 22:26:58 +08:00
ckirchhoff
Zaida Zhou
ZShaopeng
Derry Lin
cathyzhang222
q.yao
Zhang
sherie
wangjiangben-hw
VVsssssk
Yue Zhou
q.yao
ChaimZhu
takuoko
bdf
Ivan Shcheklein
CokeDong
tpoisonooo
Vasilis Vryniotis
Zachary Streeter
tripleMu
Hoantrbl
Yanhong Zeng