0a8e67f753
bump version to v1.4.6 ( #1738 )
2022-02-22 19:34:20 +08:00
3a3514a54d
fixing save checkpoint for best metric ( #1694 )
...
* fixing save checkpoint for best metric
* fixing save checkpoint for best metric v2
* Update mmcv/runner/hooks/evaluation.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* update for lint error
* fixing lint error
* fix lint
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-02-22 16:02:45 +08:00
6d440e0e0c
[Fix] Remove unused header files ( #1653 )
...
* first commit
* [Fix] Remove two unused header files
2022-02-22 15:58:16 +08:00
e7f049afa1
Add mmrotate link in README.md ( #1733 )
...
* Add mmrotate link in README.md
* Add mmrotate link in docs
* fix isort
2022-02-20 11:42:33 +08:00
b83bdb0cbe
[Refactor] Refactor the interface for RoIAlignRotated ( #1662 )
...
* fix interface for RoIAlignRotated
* Add a unit test for RoIAlignRotated
* Make a unit test for RoIAlignRotated concise
* fix interface for RoIAlignRotated
* Refactor ext_module.nms_rotated
* Lint cpp files
2022-02-18 16:59:33 +08:00
fccb10917d
Imporve the docstring of imfrombytes and fix a deprecation-warning ( #1731 )
2022-02-18 16:54:19 +08:00
c1de4c9bbf
[Feature] Add spconv ops from mmdet3d ( #1581 )
...
* add ops (spconv) of mmdet3d
* fix typo
* refactor code
* resolve comments in #1452
* fix compile error
* fix bugs
* fix bug
* transform from 'types.h' to 'extension.h'
* fix bug
* transform from 'types.h' to 'extension.h' in parrots
* add extension.h in pybind.cpp
* add unittest
* Recover code
* (1) Remove prettyprint.h
(2) Switch `T` to `scalar_t`
(3) Remove useless lines
(4) Refine example in docstring of sparse_modules.py
* (1) rename from `cu.h` to `cuh`
(2) remove useless files
(3) move cpu files to `pytorch/cpu`
* reorganize files
* Add docstring for sparse_functional.py
* use dispatcher
* remove template
* use dispatch in cuda ops
* resolve Segmentation fault
* remove useless files
* fix lint
* fix lint
* fix lint
* fix unittest in test_build_layers.py
* add tensorview into include_dirs when compiling
* recover all deleted files
* fix lint and comments
* recover setup.py
* replace tv::GPU as tv::TorchGPU & support device guard
* fix lint
Co-authored-by: hdc <hudingchang.vendor@sensetime.com>
Co-authored-by: grimoire <yaoqian@sensetime.com>
2022-02-18 15:53:10 +08:00
33c83b5afa
Support deepcopy for Config ( #1658 )
...
* Support deepcopy for Config
* Iterate the `__dict__` of Config directly.
* Use __new__ to avoid unnecessary initialization.
* Improve according to comments
2022-02-16 22:51:08 +08:00
5de2b130d3
[Docs] Fix typo in registry.md ( #1717 )
2022-02-14 10:44:18 +08:00
e36332e67d
Bump version to v1.4.5 ( #1716 )
2022-02-12 17:05:11 +08:00
b10eaedd38
[Fix] batched nms for nms_rotated ( #1688 )
...
* Fix batched_nms to support nms_rotated
* Update test code for batched_nms with nms_rotated
* Edit indexing the score in nms
* Use -1 indexing for batched_nms
2022-02-12 14:45:39 +08:00
62c1b7f68b
[Enhance] Use PyTorch HSwish implementation. ( #1709 )
...
* [Enhance] Use PyTorch HSwish implementation.
* fix conv test
* upgrade version
* add version comments
2022-02-12 14:34:35 +08:00
6e2b1067ba
[Docs] Add cuDNN installation in tensorrt_plugin.md ( #1711 )
...
* Update tensorrt_plugin.md
* Update tensorrt_plugin.md
* Update tensorrt_plugin.md
* Update tensorrt_plugin.md
2022-02-12 12:51:08 +08:00
dd82ab1497
Upgrade the version of isort ( #1705 )
...
* Upgrade the version of isort
* sort the order of importing modules
2022-02-09 21:29:21 +08:00
b0b30d0c5c
fix bug ( #1702 )
2022-02-09 14:00:12 +08:00
7df4ebedb3
[Fix] Fix the mismatch torch version of MlflowLoggerHook( #1680 )
...
* [Fix] mlflow logger error
* [Update] mlflow hook test arguments
* Replace torch.__version__ with mmcv.TORCH_VERSION
* update test code
2022-02-07 23:14:46 +08:00
26aba2f533
[Fix] Fix an incorrect assignment in the BaseTransformerLayer ( #1670 )
...
* fix BaseTransformerLayer
* Add BaseTransformerLayer unit test without ffn_cfg embed_dims
* Optimize code logic
2022-01-28 23:43:53 +08:00
26c095dc11
[Fix] Fix the undefined name error ( #1695 )
2022-01-27 20:11:32 +08:00
1231ef1cfe
bump version to v1.4.4 ( #1686 )
2022-01-24 21:21:50 +08:00
9dedc44555
[Fix] Fix the cast_tensor_type ( #1639 )
...
* [Fix] Fix the cast_tensor_type when the type of inputs is not the same as src_type
* Add note
* improve comments
2022-01-24 21:21:37 +08:00
580e374eae
Add decay to CyclicLrUpdater ( #1655 )
...
* Add decay to cyclic LR
* Simplify tests
* Fix error in tests
* fix cyclic lr
* add weight decay CyclicLrUpdate test
* Update mmcv/runner/hooks/lr_updater.py
update docstring
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* update CyclicLrUpdater unit test
* add comments to CyclicLrUpdaterHook
* fix CyclicLrUpdater. Support peak_lr decay when target[0] < 1
* add momentum decay to CyclicMomentumUpdater
* update momentum unit test
* Fix CyclicMomentum comment
Fix CyclicMomentum comment
Co-authored-by: Dmytro Panchenko <panchenkodmytry@gmail.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-01-24 19:34:25 +08:00
0448fcf906
fix the scatter when input is cpu ( #1621 )
...
* fix the scatter when input is cpu
* Update _functions.py
Add spaces to comply with the code specification
* add unittests
* add a blank line
* fix unittet
Co-authored-by: zhouzaida <zhouzaida@163.com>
2022-01-24 19:17:10 +08:00
b8d78336a7
[Fix] Align HSigmoid with pytorch official implementation( #1622 )
...
* [Fix] align hsigmoid with pytorch official
* [Fix] add warnings for Hsigmoid
* [Fix] fix format
* [Fix] add unittest
* [Fix] fix docstring
2022-01-20 14:25:10 +08:00
b6e1ab7e83
add wechat qrcode ( #1669 )
2022-01-19 22:35:36 +08:00
83df7c4b00
[Fix] Fix LoggerHooks docstring ( #1664 )
...
* [Fix] fix loggerhooks docstring
* [Fix] fix some details
* [Fix] fix docstring
* [Fix] fix docstring
* [Fix] fix docstring
* [Fix] add docstring
2022-01-19 16:10:20 +08:00
37121bf4f4
[Fix] Fix the bug of momentum updater with warmup policy ( #1626 )
...
* fix momentum updater typo bug
* Add unit test for 'constant', 'linear' and 'exp' momentum warmup policy
2022-01-18 17:33:07 +08:00
88d802ce4f
[Fix] Fix the invalid cuda memory access when training s2anet ( #1660 )
2022-01-18 15:00:17 +08:00
b04ad69d1b
[Feature] Add 6 rotated detection ops in parrots ( #1665 )
...
* add active_rotated_filter, convex_iou, min_area_polygons, points_in_polygons, riroi_align_roteted, rotated_feature_align in parrots
* fix lint
* fix lint
2022-01-17 20:59:26 +08:00
86ed509a8b
Add OpenMMLab website and platform links ( #1666 )
2022-01-13 16:40:12 +08:00
71f32244df
[Enhancement] Remove some warning logs of compilation ( #1649 )
...
* first commit
* [Enhancement] Remove some warning logs of compilation
* delete a comment
2022-01-13 14:29:06 +08:00
227037fcd3
[Fix] Fix the unit test of correlation op ( #1659 )
2022-01-13 14:27:50 +08:00
ccdc61c087
[Fix] Fix the compilation error on windows ( #1657 )
2022-01-11 12:55:07 +08:00
b5ec327d34
Fix iou3d bug in parrots ( #1656 )
2022-01-11 11:11:08 +08:00
48419395e3
Bump version to v1.4.3 ( #1654 )
2022-01-10 20:44:04 +08:00
594ff3c0d3
[Feature] Add convex IoU CUDA op for rotated detection. ( #1610 )
...
* add convex iou
* fix lint
* add convex_iou
* fix convex_iou
* add convex_giou
* fix bug
* fix lint
* fix bug
* Update
* update
* add kernel loop
* fix bug.
* fix polygen typo
* simplify reverse
* Update convex_iou_cuda_kernel.cuh
* Update mmcv/ops/convex_iou.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/convex_iou.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* add AT_DISPATCH_FLOATING_TYPES_AND_HALF
* fix lint
* fix lint
* Resolving conflicts
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-01-10 20:43:12 +08:00
9acc892a44
[Feature] Add active rotated filter op for rotated detection. ( #1598 )
...
* add active_rotated_filter
* fix lint
* fix lint
* renaming nRotation and nOrientation
* Update active_rotated_filter_cuda_kernel.cuh
* Update active_rotated_filter_cuda.cu
* fix bug
* fix lint
* Update test_active_rotated_filter.py
* fix lint
* Update active_rotated_filter_cuda_kernel.cuh
* renaming
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* fix lint
* Resolving conflicts
* fix lint.
* Update __init__.py
* Update mmcv/ops/csrc/pytorch/cuda/active_rotated_filter_cuda.cu
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update active_rotated_filter.cpp
* fix lint
* Update mmcv/ops/csrc/pytorch/cpu/active_rotated_filter.cpp
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/csrc/pytorch/cpu/active_rotated_filter.cpp
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update active_rotated_filter.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-01-10 17:35:20 +08:00
40518322b6
add artifact logging to wandb hook ( #1616 )
...
* add artifact logging to wandb hook
* upload artifacts wiwth only specified suffix
* update docstring
* Update mmcv/runner/hooks/logger/wandb.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* fix linting
* add tests for wandb artifact logging
* remove redundant lines
* fix wandb tests
* init `WandbLoggerHook` with `log_artifact=True` in tests
* remove redundant lines from wandb tests
* add docstring for `with_step`
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-01-10 16:52:38 +08:00
8abb3b2909
Deprecate the support for "python setup.py test" ( #1637 )
...
* Remove the unnecessary dependency pytest-runner
* remove the tests_requires option from setup.py
2022-01-10 16:28:25 +08:00
ff83e502a3
[Docs] Add the link of mmdeploy ( #1638 )
2022-01-10 16:26:37 +08:00
51b40c332a
[Feature] Add min_area_polygons CUDA op for rotated detection. ( #1611 )
...
* init
* Update pybind.cpp
* Update min_area_polygons_cuda.cuh
* Update cudabind.cpp
* fix bug
* Create test_min_area_polygons.py
* add test
* update
* Update min_area_polygons_cuda.cuh
* fix bugs.
* Update min_area_polygons_cuda.cuh
* Update min_area_polygons.py
* Update min_area_polygons_cuda.cuh
* merge these 4 nested loops
* add AT_DISPATCH_FLOATING_TYPES_AND_HALF
* fix lint
* Resolving conflicts
2022-01-10 11:00:50 +08:00
b6167d5987
[Enhancement] Add clockwise argument to ops box_iou_rotated and nms_rotated ( #1592 )
...
* add clockwise arguments to ops box_iou_rotated and nms_rotated
* refactor docs
* change code that may incur stopped gradient.
* refactor docs
* Update mmcv/ops/nms.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/box_iou_rotated.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2022-01-10 10:57:11 +08:00
b586cc2f6a
[Refactor] Replace DIVUP with GET_BLOCKS ( #1586 )
...
* [Improve] migrating DIVUP to GET_BLOCKS
* [Fix] use GET_BLOCKS only for block alloc and del useless statements
* [Fix] add kernel loop for nms and del useless statements
2022-01-08 11:35:16 +08:00
cf754db983
Fix the cuda compilation error on Windows ( #1643 )
2022-01-07 21:54:17 +08:00
d30e37d4d5
[Refactor] refactor requirements ( #1536 )
...
* [Improve] build using ninja
* [Refactor] refactor requirements
* [Improve] imporve docs
* [Fix] fix file name
2021-12-29 23:15:11 +08:00
e1d6ea8c87
bump version to v1.4.2 ( #1609 )
2021-12-24 15:32:01 +08:00
d68119c1fe
[Docs] Add the link of mmrazor ( #1612 )
...
* Add the link of mmrazor
* Add the link of mmrazor
2021-12-24 15:31:49 +08:00
304efbb650
[Feature] Add points_in_polygons CUDA op for rotated detection. ( #1600 )
2021-12-24 10:56:48 +08:00
a4dc2a72ab
support device dispatch in parrots ( #1588 )
2021-12-24 00:30:54 +08:00
0bcbeadb53
[Feature] Add RiRoIAlignRotated CUDA op for rotated detection. ( #1599 )
2021-12-24 00:30:34 +08:00
2475dc3452
[Feature] Add feature refine CUDA op for rotated detection. ( #1603 )
...
* re PR
* replace all the feature_refine with rotated_feature_align
* replace all the FR with RotatedFeatureAlign
* Update mmcv/ops/rotated_feature_align.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/rotated_feature_align.py
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* fix lint
* Update mmcv/ops/csrc/pytorch/cuda/rotated_feature_align_cuda.cu
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/csrc/pytorch/cuda/cudabind.cpp
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/csrc/pytorch/cuda/rotated_feature_align_cuda.cu
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/csrc/pytorch/cuda/rotated_feature_align_cuda.cu
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* Update mmcv/ops/csrc/pytorch/cuda/rotated_feature_align_cuda.cu
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
* fix lint
* Update cudabind.cpp
* Update cudabind.cpp
* fix bug in test. & add backward test
* fix lint
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
2021-12-23 17:38:58 +08:00
Zaida Zhou
makifozkanoglu
Hakjin Lee
Jiazhen Wang
Wenhao Wu
Ma Zerun
Ren Tianhe
RangiLyu
Jamie
Yue Zhou
Mashiro
bilibilee
imyhxy
zhanggefan
pc
fatih
LudoBar