mirrors
/
mmcv
mirror of https://github.com/open-mmlab/mmcv.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
747 Commits
13 Branches
108 Tags
42 MiB
Commit Graph

747 Commits (1b59409e94c69cfc8a4dd3e0fa55f02d0ae281d3)
 

Author SHA1 Message Date
Zaida Zhou 1b59409e94
bump version to v1.3.7 (#1103) 2021-06-16 19:15:58 +08:00
Shilong Zhang 088fde3541
Avoid bc-breaking of importing `MultiScaleDeformableAttention` (#1100) 
* avoid bc-breaking

* fix function name

* fix typo

* fix import

* add import warning

* remove wapper

* remove unitest

* add dep warning

* add dep warning
 2021-06-16 13:48:12 +08:00
Weiwen Chen a5d4c6528f
add a return value in TextLoggerHook.log() (#1040) 
I need this in a subclass, but I dont want copy the whole `log()` function
 2021-06-14 21:21:29 +08:00
Zaida Zhou 6cb534b775
bump version to v1.3.6 (#1095) 2021-06-11 21:04:53 +08:00
LXXXXR c9b009f1ba
fix typo (#1094) 2021-06-11 20:08:08 +08:00
pc 3d7bcc8fe2
add border_align support in parrots (#1086) 2021-06-11 18:11:43 +08:00
Shilong Zhang e05fb56031
Refactor the baseclass related to transformer (#978) 
* minor changes

* change to modulist

* change to Sequential

* replace dropout with attn_drop and proj_drop in MultiheadAttention

* add operation_name for attn

* add drop path and move all ffn args to ffncfgs

* fix typo

* fix a bug when use default value of ffn_cfgs

* fix ffns

* add deprecate warning

* fix deprecate warning

* change to pop kwargs

* support register FFN of transformer

* support batch first

* fix batch first wapper

* fix forward wapper

* fix typo

* fix lint

* add unitest for transformer

* fix unitest

* fix equal

* use allclose

* fix comments

* fix comments

* change configdict to dict

* move drop to a file

* add comments for drop path

* add noqa 501

* move bnc wapper to MultiheadAttention

* move bnc wapper to MultiheadAttention

* use dep warning

* resolve comments

* add unitest:

* rename residual to identity

* revert runner

* msda residual to identity

* rename inp_identity to identity

* fix name

* fix transformer

* remove key in msda

* remove assert for key

Co-authored-by: HIT-cwh <2892770585@qq.com>
Co-authored-by: bkhuang <congee524@gmail.com>
Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
 2021-06-11 18:09:31 +08:00
Y. Xiong 11629d5268
Support resume for fp16 training (#1013) 
* fix cast nn.Module bug

* fix misleading doc

* add resume function

* del useless; fix typo

* change meta structure; set resume default
 2021-06-11 16:35:51 +08:00
pc 69146fe3d7
add load_ext warning (#1089) 2021-06-11 16:30:39 +08:00
Dmitry Sidnev a88d1d28c1
[Feature] enable exporting to onnx for PointRend (#953) 
* Fix export to onnx for PointRend

* Fix codestyle

* Fix codestyle

* Fix type in docstring

* Minor fix

* Fix export with custom ops

* Fix codestyle

* Add tests for bilinear_grid_sample function

* Remove redundant operation and rename variables

* Fix bug in bilinear_grid_sample and update test

* Fix getting batch size

* skip torch==1.3.1

* remove unused import

* fix lint

* support export with batch

* fix dynamic clip

* skip test for torch<1.5.0

* Add docstrings and comments

* Minor fix

* Recover clipping code

* Fix clamping in pytorch 1.7.0

* Fix bilinear_grid_sampler

* Minor fix

Co-authored-by: maningsheng <maningsheng@sensetime.com>
 2021-06-11 13:49:19 +08:00
LXXXXR 1076958cd4
[Docs] Add runner tutorial (#1082) 
* add runner doc

* revised according to comments and remove non existing links

* revise according to comments
 2021-06-09 22:41:02 +08:00
David de la Iglesia Castro bdd7022143
Add DvcliveLoggerHook (#1075) 
* Add dvclive logger hook

* Move docstring to class

* docstring updates
 2021-06-08 22:20:33 +08:00
Miao Zheng d212bd53b1
[Fix] Fix the docstring for initializers (#1071) 
* [WIP] Updata initialization documents

* [Fix] Fix the docstring for initializers
 2021-06-01 23:16:13 +08:00
lizz 50537ddfd4
Imporve windows support for list_from_file (#1043) 
Signed-off-by: lizz <lizz@sensetime.com>
 2021-06-01 23:04:02 +08:00
LXXXXR b028a1f967
Fix mmcls link (#1067) 2021-06-01 22:45:35 +08:00
Miao Zheng 50c255bc2d
[Feature] Support to use name of the base classes in init_cfg (#1057) 
* [Fix] Support names of base classes matching in init_cfg

* revise bool to len
 2021-06-01 22:35:19 +08:00
SemyonBevzuk bf2c9fa8d2
[Feature] NMS update (#957) 
* Add score_threshold and max_num to NMS

* Fix codestyle

* Fix codestyle

* Fix inds in nms

* Update nms docstring

* Move score_threshold and max_num arguments

* Fix args order in docstring

* fix lint of c++ file

* Remove torch.onnx.is_in_onnx_export() and add max_num to batched_nms for separate classes.

* Rewrote max_num handling in NMSop.symbolic

* Added processing max_output_boxes_per_class when exporting to TensorRT

* Added score_threshold and max_num for NMS in test_onnx.py and test_tensorrt.py

* Remove _is_value(max_num)

* fix ci errors with torch==1.3.1

* Update test_batched_nms in test_nms.py

* Added tests for preprocess_onnx

* Moved 'test_tensorrt_preprocess.py' and 'preprocess', updated 'remove_tmp_file'.

* Update mmcv/tensorrt/__init__.py

* Fix segfault torch==1.3.1 (remove onnx.checker.check_model)

* Returned 'onnx.checker.check_model' with torch version check

* Changed torch version from 1.3.1 to 1.4.0

* update version check

* remove check for onnx

Co-authored-by: maningsheng <maningsheng@sensetime.com>
 2021-05-31 23:42:26 +08:00
Yinhao Li 717d15719c
Add segmentation keys for greater_keys. (#1060) 2021-05-31 10:13:55 +08:00
Zaida Zhou e728608ac9
Bump version to v1.3.5 (#1050) 2021-05-25 22:50:53 +08:00
RunningLeon 4d42365ac2
[Feature]: add TensorRT InstanceNormalization plugin (#1034) 
* add instancenorm plugin

* resolve comments

* fix lint

* fix typo
 2021-05-25 20:03:57 +08:00
v-qjqs 6c7d6c32ee
Supports cuda version BorderAlign module (#1021) 
* support cuda version `BorderAlign` module

* fix symbolic

* merge

* fix cpp lint error

* add unit test

* add comments for code references

* reformat doc

* fix lint error

* fix conflict
 2021-05-25 15:23:11 +08:00
pc 732ff5093e
Add ms_deformable_attn in parrots (#1042) 2021-05-25 13:13:05 +08:00
Zaida Zhou a637724052
[Fix] Delete commit id (#1045) 2021-05-25 12:48:17 +08:00
lizz 13888df2aa
Fix typos (#1041) 
* Fix typos

Signed-off-by: lizz <lizz@sensetime.com>

* Add deprecation warning

Signed-off-by: lizz <lizz@sensetime.com>
 2021-05-24 14:51:45 +08:00
q.yao 9d1436fb6c
[Feature] add cummax/cummin tensorrt plugin (#1031) 
* add cummax/cummin tensorrt plugin

* fix isort

* fix with clang-format

* fix with clang-format again

* add document
 2021-05-24 13:55:21 +08:00
Zaida Zhou 55b4847a41
[Feature] Add truncated normal weight init (#935) 
* [Feature] Add truncated normal weight init

* [Feature] Add truncated normal weight init

* [Feature] Add truncated normal weight init

* update docstring

* delete modelA.pth

* modify according to comment

* use kstest to check truncated normal

* delete modelA.pth

* fix test.txt
 2021-05-23 20:54:54 +08:00
Guangchen Lin 4bd3b5027a
[Fix] Support amp (pytorch >= 1.6.0) on DCN and DCNv2/ Add unit tests on DCN/DCNv2 amp (#1029) 
* fix fp16 bug on DCNv2

* support fp16 on DCN/DCNv2 when pytorch >= '1.6.0'

* add comment

* Modified the comments

* Unified the usages of '.to()' and '.type_as()'
 2021-05-23 17:42:59 +08:00
fcakyon e9f2a02b47
add neptune.ai logger hook (#1025) 
* add neptune.ai logger hook

* add docstring

* move docstring

* update docstr

* update before_run
 2021-05-23 15:28:21 +08:00
Zaida Zhou d3bbfdb899
fix parrots ci (#1032) 2021-05-23 15:23:58 +08:00
Guangchen Lin 5be9593499
[Fix] fix generalized attention fp16 (#1036) 
* fix generalized attention fp16

* fix building without gpu error

* add comment

* Cast tensor at initialization
 2021-05-23 15:16:27 +08:00
ritosonn 1a66977f33
[fix]: Fix a bug where logs are missing when two or more loggers were set (#1015) 
* +super().before_run()

* flip reset_flag
 2021-05-20 08:52:28 +08:00
Zaida Zhou b8c09f3b84
Bump version to v1.3.4 (#1024) 2021-05-13 22:52:19 +08:00
WRH 8ee8f696f0
[Fix] Read in rb mode then decode (#983) 
* read in rb mode then decode

* Update config.py

* Update .pre-commit-config.yaml

* Update config.py

* Update config.py

Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
 2021-05-13 22:39:18 +08:00
Rui Xu b1df16a409
[LICENSE] Add more information for license (#956) 
* add license

* fix lint

* fix some discription

* fix some discriptions and dirty marks

* fix format

* revise some words

* Update README_zh-CN.md

* Update README_zh-CN.md

Co-authored-by: Wenwei Zhang <40779233+ZwwWayne@users.noreply.github.com>
 2021-05-13 21:55:44 +08:00
LXXXXR d7f8355011
[Fix] Fix load_ckpt from pavi and s3 (#1020) 
* fix load_ckpt

* revised according to comments

* revise according to comments

* fix typo
 2021-05-13 20:55:51 +08:00
Yezhen Cong b36c4de157
[Fix] Fix wrong iter number and progress number in the logging during val/test time (#914) 
* Remove iter number in logging during val/test time

* Fix typo

* modified EvalHook for eval mode to print the correct iter number
 2021-05-13 20:32:33 +08:00
Zaida Zhou a1d3bf1c80
[Docs] Update weight initialization in cnn.md (#912) 
* [Docs] Update weight initialization in cnn.md

* Update cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* [Docs] Update weight initialization in cnn.md

* modify docs according to comments

* modify docs for weight init according to the comment

* change init_weight() to init_weights()

* modify according to comment
 2021-05-13 20:29:36 +08:00
Ma Zerun 15bcaa9c05
Add custom hook by config file (#970) 
* Assign different priority to default hooks, and add custom hook register in base runner.

* Add custom hook register in example train file

* Add unittest of custom hook

* Code format
 2021-05-13 20:29:17 +08:00
Shilong Zhang 9b8dd0835d
[fix]: fix softnms (#1019) 
* fix basemodule

* fix typo

* fix unitest
 2021-05-13 14:04:54 +08:00
Shilong Zhang da0711461c
[Fix]: fix basemodule (#1018) 
* fix basemodule

* add commnet
 2021-05-13 14:02:59 +08:00
Jintao Lin 4c2b05f9b8
Load `hook_msgs` when resume checkpoint (#962) 2021-05-13 09:54:38 +08:00
jeffreykuang 2623fbf21c
Add pixel group and contour expand ops (#993) 
* add pixel group ops

* reformatting

* formatting&rm auto

* Add citation

* Add contour expand

* c++ linting

* Add unit tests with Tensor

* rm model.pth

* rename

* c++ linting

* c++ linting

* Rename variables
 2021-05-12 10:41:22 +08:00
Ziyi Wu c77e95a65f
[Enhance] Add step momentum updater to support MMDet3D (#1011) 
* add StepMomentumUpdaterHook

* add unit test

* fix typos

* refactor step updater

* replace stage with exp

* fix linting error

* use all() operation
 2021-05-11 20:06:04 +08:00
gengenkai 1a5bf76237
[Enhancement] LR triangular (#1001) 
* [Fix] lr add triangular

* [Fix] lr_triangular

* lr add docstring

* lr add docstring

* add unittest of triangular lr update
 2021-05-11 13:25:43 +08:00
Yosuke Shinya 479624672a
[Fix] Fix DCN fp16 (#1014) 
* [Fix] Fix DCN fp16

* add comment
 2021-05-11 13:16:23 +08:00
lizz f61295d944
Add test util for checking stand-alone python scripts (#1007) 
* Add test util for checking stand-alone scripts

Signed-off-by: lizz <lizz@sensetime.com>

* Restrict to python scripts

Signed-off-by: lizz <lizz@sensetime.com>

* fix

Signed-off-by: lizz <lizz@sensetime.com>

* tiny

Signed-off-by: lizz <lizz@sensetime.com>

* Allow no capture

Signed-off-by: lizz <lizz@sensetime.com>

* Simplify interface

Signed-off-by: lizz <lizz@sensetime.com>

* Technical notes

Signed-off-by: lizz <lizz@sensetime.com>

* tiny

Signed-off-by: lizz <lizz@sensetime.com>

* Update hello.py

* Update test_testing.py

* Update test_testing.py
 2021-05-10 22:15:35 +08:00
v-qjqs 934b549e23
Support custom operators cummax and cummin for onnxruntime (#1010) 
* support custom op `mmcv::cummax` for onnxruntime in mmcv

* fix clang-format lint error

* support mmcv::cummin, reformat codes

* fix merge from master

* add docs for mmcv::cummax and mmcv::cummin

* format doc

* add assertion for torch version, when exporting `cummax` to onnx

* add more comments for torch version

* handle exporting to onnx in `soft_nms`

* commit for test_onnx

* remove `is_in_onnx_export` in softnms

* add more comments

* fix c++ lint error

* add known issues doc for `cummax`

* fix known issues doc
 2021-05-10 21:33:27 +08:00
v-qjqs db6b0542c7
[Feature]: Support corner_pool related custom operators for onnxruntime in mmcv (#997) 
* supports for onnxruntime custom op `mmcv::MMCVTopPool`

* supports for onnxruntime custom op `mmcv::MMCVCornerPool`, involving TopPool, BottomPool, LeftPool and RightPool

* add unittest for corner_pool

* supports mmcv::CornerPool without memcpy

* add docs for mmcv::CornerPool

* re-add docs for mmcv::CornerPool

* fix output dtype doc

* reformat

* format with pre-commit

* format

* fix lint error, by using google clang-format style for c/c++
 2021-05-01 16:28:25 +08:00
Zaida Zhou 3f8e985b02
Bump version to v1.3.3 (#1009) 2021-04-30 19:08:04 +08:00
Zaida Zhou c4aa4146f5
Bump version to v1.3.2 (#1006) 2021-04-29 19:38:03 +08:00