e8489a7b4b
Add case case_sensitive in scandir ( #1389 )
...
* add case_insensitive
* rename v
* case_insensitive to case_sensitive
* Update docstring
2021-10-20 14:34:34 +08:00
c85c240fd8
[Docs] Fix error when building pdf ( #1414 )
...
* [Docs] Fix error when building pdf
* fix link
2021-10-20 14:33:40 +08:00
76cfd77b3a
Fix config parsing error caused by non-ascii characters ( #1410 )
...
* explicitly set encoding as 'utf-8'
2021-10-20 14:32:38 +08:00
ba334b43dd
修改语病 ( #1411 )
2021-10-20 14:25:59 +08:00
ce58fd6fcb
add device DeviceGuard ( #1402 )
2021-10-20 13:27:26 +08:00
c50184630c
bump version to v1.3.15 ( #1408 )
2021-10-15 20:43:53 +08:00
91b8478c84
Reduce ms_deformable_attn test memory usage ( #1407 )
2021-10-15 19:49:39 +08:00
b484abac09
Fix furthest_sample_point ( #1405 )
2021-10-15 17:30:04 +08:00
5c25ae1a19
[Feature] Add roipoint_pool3d op from mmdet3d ( #1358 )
...
* add ops (roipoint_pool3d) in mmdet3d
* refactor code
* fix typo
* add unit test
* refactor code
* refactor code
* refactor code
* fix typo
2021-10-15 17:15:53 +08:00
e99bfce608
[Feature] Add assign_score_withk op for paconv from mmdet3d ( #1357 )
...
* add ops (assign_score_withk) in mmdet3d
* add ops (assign_score_withk) in mmdet3d
* refactor code
* fix typo
* refactor code
* fix typo
* polish docstring
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-10-15 13:18:31 +08:00
be5841e45d
[Feature] Add interpolate ops from mmdet3d ( #1355 )
...
* add ops (interpolate) in mmdet3d
* refactor code
* fix typo
* fix typo
* fix typo
* refactor code
2021-10-14 20:51:02 +08:00
97e5bada4c
continue PR #1223 ( #1404 )
...
* fix MultiScaleDeformableAttention inference issue on cpu model
* fix lint
* add unintest
* remove some code
* Update tests/test_ops/test_ms_deformable_attn.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* fix device
* remove device
* add more device
* refactor unittest
Co-authored-by: zhicheng huang <zhichenghzc@gmail.com>
Co-authored-by: zhangshilong <2392587229zsl@gmail.com>
Co-authored-by: Shilong Zhang <61961338+jshilong@users.noreply.github.com>
2021-10-14 20:50:38 +08:00
1cd01db935
[Feature] Add gather points op from mmdet3d ( #1338 )
...
* add ops (gather points) in mmdet3d
* add ops (gather points) in mmdet3d
* refactor code
* refactor code
* fix typo
2021-10-14 16:58:12 +08:00
70f902bb9c
[Enhancement] Add error handler when getting host failed ( #1374 )
...
* [Enhancement] Add error handler when getting host failed
Signed-off-by: del-zhenwu <zhenxiang.li@zilliz.com>
* [Enhancement] Add error handler when getting host failed
Signed-off-by: del-zhenwu <zhenxiang.li@zilliz.com>
* [Enhancement] Add error handler when getting host failed
Signed-off-by: del-zhenwu <zhenxiang.li@zilliz.com>
* [Enhancement] Add error handler when getting host failed
Signed-off-by: del-zhenwu <zhenxiang.li@zilliz.com>
2021-10-14 13:49:45 +08:00
42c9e71120
[Feature] Add knn op from mmdet3d ( #1354 )
...
* add ops (knn) in mmdet3d
* refactor code
* refactor code
* fix typo
* fix typo
* fix typo
* refactor code
* refactor code
* spell typo
* fix spell typo
2021-10-14 13:33:13 +08:00
8016d88067
fix dcn compile error in parrots ( #1378 )
2021-10-13 21:02:34 +08:00
fa22d9db4e
Fix potiential bug in `deprecated_api_warning` ( #1395 )
...
* assert both dep and new args exist at same time
* add unintest
* Update tests/test_utils/test_misc.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update tests/test_utils/test_misc.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* polish warning
* polish warning
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-10-13 20:53:11 +08:00
63a6cbe913
[Feature] Add fps op from mmdet3d ( #1337 )
...
* add ops (furthest point sample) in mmdet3d
* refactor code
* refactor code
* fix typo
* fix typo
* fix typo
* refactor code
* fix typo
* define DIVUP in common_cuda_helper.hpp
2021-10-13 20:39:31 +08:00
599163e645
Add Deformable Conv CustomOp for onnxruntime ( #1343 )
...
* add onnx dcn
* replace gemm with torch C++ api
* small update
* fix cpp clang format
* pefer generic GEMM than torch ATen library
* addressing comments
* add ops path check
2021-10-13 20:28:24 +08:00
48d5b095a2
Polish readme ( #1320 )
...
* [Docs] Polish README
* [Docs] Polish README
* [Docs] Polish README
* fix typo
* update qq link
* fix typo
* update LICENSES.md
2021-10-13 20:25:49 +08:00
882822e090
[Fix] Fix the weight initialization of deform conv ( #1262 )
...
* Update deform_conv.py
* polish the docstring of reset_parameters
* change the initialization of `self.weight`
switch the initialization of `self.weight` to the standard kaiming method
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-10-13 20:16:28 +08:00
f22c9eb4a4
Add code spell hook to pre-commit and fix typos ( #1384 )
...
* Add code-spell hook to pre-commit
* Add code-spell hook to pre-commit and fix typos
* fix setup.cfg
2021-10-04 20:13:54 +08:00
c934605e83
Switch to the docker image provided by PyTorch ( #1376 )
2021-10-03 10:29:05 +08:00
8cac7c25ee
[Refactor] Remove outdated code ( #1370 )
2021-09-26 21:14:49 +08:00
a90b3978db
[Fix] Unrecognized symbol in correlation.cpp ( #1372 )
2021-09-26 11:24:03 +08:00
745aa7373e
[Fix] Revise unit test of correlation ( #1368 )
...
* [Fix] Revise unit test of correlation
* rename
* lint
* lint
* lint
* lint
2021-09-25 21:13:34 +08:00
9d4571e3d0
[Docs] Translate contributing documentation ( #1351 )
...
* [Docs] Translate contributing documentation
* polish translation
* fix typo
* fix typo
2021-09-24 17:26:15 +08:00
f69a3a44e3
[Docs] Translate building documentation ( #1353 )
...
* [Docs] Translate building documentation
* polish translation
2021-09-24 17:02:59 +08:00
afe0794ce8
[Docs] Add docs_zh_CN of TensorRT ( #1336 )
...
* Add docs_zh_CN of TensorRT
* fix according to doc-cn-onnx
* update doc of cummax cummin
* Apply suggestions from code review
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* update heading
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-09-24 17:00:35 +08:00
2b39d7a8ec
[Docs] Add zh_cn document of ONNX ( #1331 )
...
* add doc-cn of ONNX
* Update docs_zh_CN/deployment/onnxruntime_custom_ops.md
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 doc of cummax
* fix en doc of softnms
* update heading
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-09-24 16:57:20 +08:00
6f533ff113
[Docs] cnn.md translated ( #1246 )
...
* cnn.md translated
* polish translation
* polish translation
Co-authored-by: zhouzaida <zhouzaida@163.com>
2021-09-24 16:54:32 +08:00
be945648c4
bump version to v1.3.14 ( #1364 )
2021-09-23 21:27:33 +08:00
324e9f18ff
[Features] Load optical flow data from bytes ( #1362 )
...
* [Features] Load optical flow data from bytes
* docstring
* revise base on comments
* compression test data
* compression test data
* docstring
* minors
2021-09-23 21:25:59 +08:00
b92ea0b5df
[Feature] Add Correlation CUDA op ( #1361 )
2021-09-23 21:08:41 +08:00
f3dfc4135b
[Feature] Add ballquery op from mmdet3d ( #1332 )
2021-09-23 21:08:00 +08:00
4e101e0b75
[Feature]: Support empty tensor in MMSyncBN ( #1205 )
...
* [Feature]: support empty tensor in MMSyncBN
* refine code
* resolve comments
* clean unnecessary comments
* fix inaccurate statistics when empty tensor
* resolve comments and add docstrings
* update unit tests
* rephrase, ready for merge
2021-09-23 17:10:38 +08:00
b6eb3822ad
add contour_expand and pixel_group in parrots ( #1323 )
2021-09-23 11:42:19 +08:00
4bab29241a
[Docs] Translate visualization documentation ( #1350 )
2021-09-21 13:55:19 +08:00
fb02e81a12
[Docs] Translate ops documentation ( #1349 )
2021-09-21 13:54:37 +08:00
1216e5fe7f
[Docs] Use PyTorch sphinx theme ( #1321 )
...
* [Docs] Use PyTorch sphinx theme
* add sphinx-copybutton
* add twitter and zhihu link
* remove shpinx_rtd_theme from doc.xtx
* update docs.txt
* update conf.py
2021-09-14 16:35:41 +08:00
6434d0d7e2
[Docs] Translate understand_mmcv about registry.md and fix config.md ( #1204 )
...
* Add Chinese translation of config.md.
* Add Chinese translation of registry.md and fix config.md
* Update config.md
* Update registry.md
* Update config.md
* Update config.md
* Update registry.md
* Update config.md
* fix format
* polish translation
* polish translation
* polish translation
Co-authored-by: zhouzaida <zhouzaida@163.com>
2021-09-13 13:16:19 +08:00
b4bfeb53c5
bump version to v1.3.13 ( #1327 )
2021-09-09 23:48:27 +08:00
2a3d2d4a35
Reimplement cc_attention using pure pytorch ( #1201 )
...
* Reimplement cc_attention using pure pytorch
* fix: avoid BC-Breaking
* delete cc_attention related cpp and cuda files
* delete cc_attention related lines in pybind.cpp
* make out Tensor contiguous.
* remove unneeded lines.
* Update mmcv/ops/cc_attention.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update TestCrissCrossAttention
* passing pre-commit
* Update docstring of CrissCrossAttention
* Update docstring of CrissCrossAttention
* Update mmcv/ops/cc_attention.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* [docs]polish the docstring
* [Docs] Polish the docstring
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-09-09 21:53:45 +08:00
642d281823
[Feature] Add revert_sync_batchnorm ( #1253 )
...
* [Feature] Add revert_sync_batchnorm
* support mmsyncbn (to be tested)
* Test passed
* Update docstring, rename the test file
* remove test_sync_bn
* add comment
* add mmcv.ops check
* Add a comment
* Add notes and relax test req
Co-authored-by: gaotongxiao <gaotongxiao@gmail.con>
2021-09-08 10:59:39 +08:00
99088c81a8
[Fix] Restrict the warning message ( #1267 )
...
* restrict the warning message
* and an important keyword in warning description
* a more elegant way of condition
* link format code too long
* fix the stupid spelling mistake
* Use issubclass to restrict warning message.
* maybe this version is more elegant.
* conv + bias + norm warning pytest
* 'created' a warning, hahaha
* isort and yapf format revision
* isort and yapf format revision
* flake8 fail issue
* I have to right this way in order to solve the conflicts between yapf and flake8, sigh...
* fixed test bug
* Add ruby windows installer source.
* Simplified the code and remove ruby source from CONTRIBUTING.md
* use _BatchNorm to simplify the code
* bug fix and add instanceNorm case into warning
* change the warning message to make it more clear
* fix unit test
2021-09-07 19:45:14 +08:00
eed9cced8e
[Enhancement] Enhance the output of exception ( #1309 )
2021-09-07 19:35:53 +08:00
4f4eb27514
translation of faq.md ( #1251 )
2021-09-07 18:20:28 +08:00
f5c28a6e08
[Fix] Fix missing `state_dict._metadata` when saving and loading checkpoints. ( #1294 )
...
* Fix missing `state_dict._metadata` when saving & loading checkpoints.
* Add unit tests.
* Fix default value and variable names in unit tests.
2021-09-07 17:53:33 +08:00
9016fef560
Fix typo on pip install mmcv-full torch1.9 cpu ( #1313 )
...
* Fix typo on pip install mmcv-full torch1.9 cpu
* 修改 pip install mmcv-full torch1.9 cpu 的错别字
* Fix typos in installation.md
Point to https://download.openmmlab.com/mmcv/dist/cpu/torch1.9.0/index.html
2021-09-07 17:32:11 +08:00
d3b0572408
Add citation ( #1303 )
2021-09-01 19:20:01 +08:00
Ezra-Yu
Zaida Zhou
Yining Li
Mr.Li
Shilong Zhang
q.yao
dingchang
del-zhenwu
pc
Eugene Liu
Fu0511
Miao Zheng
Ty Feng
Wenwei Zhang
AluminiumOxide
Leojc
Tong Gao
young
EricKani
Ma Zerun
Wei Ji