935ba78b39
[Fix] Fix skip_layer for RF-Next ( #2489 )
...
* judge skip_layer by fullname
* lint
* skip_layer first
* update unit test
2022-12-28 15:27:34 +08:00
6e3827d02b
[Feature] Support receptive field search of CNN models ( #2056 )
...
* 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>
2022-11-22 19:15:55 +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
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
55c51e1734
[Feature] Register a new activatation layer SiLU to ACTIVATION_LAYERS ( #2256 )
2022-09-13 22:38:23 +08:00
14c3e175fa
[Fix] num_channels can not be divisible by num_groups in test_build_norm_layer ( #2085 )
2022-06-30 19:28:34 +08:00
45fa3e44a2
Add pyupgrade pre-commit hook ( #1937 )
...
* add pyupgrade
* add options for pyupgrade
* minor refinement
2022-05-18 11:47:14 +08:00
e70a318ae9
[Fix] Fix parrots unit tests ( #1913 )
2022-05-09 16:59:32 +08:00
6e9ce18323
Add copyright pre-commit-hook ( #1742 )
...
* first commit
* Add copyright pre-commit-hook
2022-02-24 09:24:25 +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
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
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
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
fb486b96fd
[Fix] Fix some warnings in unittest ( #1522 )
...
* [Fix] fix some warnings in unittest
* [Impl] standardize some warnings
* [Fix] fix warning type in test_deprecation
* [Fix] fix warning type
* [Fix] continue fixing
* [Fix] fix some details
* [Fix] fix docstring
* [Fix] del useless statement
* [Fix] keep compatibility for torch < 1.5.0
2021-12-22 10:57:10 +08:00
001f3f6610
[Feature]Add patch embed and patch merge ( #1305 )
2021-12-14 21:52:37 +08:00
c522b47e6a
fix the wrong function reference bug in BaseTransformerLayer when batch_first is True ( #1418 )
2021-11-02 20:57:50 +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
c47c9196d0
[Docs] Add header for files ( #1181 )
...
* [Docs] Add header for files
* change to OpenMMLab
* add headers for .cpp, .cu, .h, .cuh
* replace Open-MMLab with OpenMMLab
2021-08-08 22:10:55 +08:00
9c26a1049e
empty tensor inference backward compatible ( #1131 )
...
* empty tensor inference backward continity
* update
* add 3d
2021-06-24 17:04:03 +08:00
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
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
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
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
2fadb1a5ec
[Fix] Revise override in init_cfg ( #930 )
...
* [Fix] Config deep copy in initialize_override
* add asserts&comments
* add test
* test org init_cfg
* test override without name
* typo
2021-04-12 14:05:28 +08:00
375605fba8
add model registry ( #760 )
...
* add model registry
* fixed infer scoep
* fixed build func
* add docstring
* add md
* support multi level
* clean comments
* add docs
* fixed parent
* add more doc
* add value error, add docstring
* fixed docs
* change to local/global search
* resolve comments
* fixed test
* update some docstring
* update docs (minior)
* update docs
* update docs
2021-04-10 21:33:34 +08:00
65fec73509
[Refactoring] Revise function of layers and override keys in init_cfg ( #893 )
...
* [Refactoring]Approve init_cfg
* revise unit test
* revise according to comments
* add comment for wholemodule
2021-03-26 16:57:59 +08:00
5f5e8e83c2
[Refactoring] Add Caffe2Xavier Initializer ( #902 )
...
* [Refactoring] Add Caffe2Xavier Initializer
* fix lint
2021-03-24 13:25:36 +08:00
371a21728f
fix bug of convmodule ( #889 )
...
* fix bug of convmodule
* fix bug of convmodule
* fix unitest
* remove assert
2021-03-20 23:08:20 +08:00
97730c2316
[Feature] support to calculate FLOPs of GN, IN, LN ( #897 )
...
* [Feature] support to calculate FLOPs of GN, IN, LN
* Update flops_counter.py
* Update flops_counter.py
2021-03-19 14:04:49 +08:00
a4c3702628
add initializers and BaseModule for unified parameter initialization ( #780 )
...
* add initializers and BaseModule for unified parameter initialization
* fix circle import
* bug fix
* add is_init flag in BaseModule
* fix docstring
* sort import and fix doc format
* fix bug
* fix docformat and double quote string
* fix import sort
* import sort
* sort import
* revise according to comments
* fix doc format
* revise according to comments
* revise import and fix typo
* polish code
* revise minors
* revice minors
* revise apply function
* revise bias initialization with probability
* add type test for bias_prob
* revise minors
2021-02-07 11:13:57 +08:00
655f3c3fe9
fix mmcv_ci test_wrappers.py for parrots ( #758 )
2020-12-24 19:50:46 +08:00
826d3a7b68
[Bug] Avoid recursion error when using customized norm layer without _abbr_ ( #732 )
...
* avoid recursion error when using customized norm layer without _abbr_
* fix unittest bug
2020-12-22 10:19:52 +08:00
cd96a84add
[Feature] Add clamp activation layer. ( #685 )
...
* add clamp without unittest
* add clamp-act with unit test
* fix name bug
* use logical and
* fix logical_and
* fix linting
* rename ClampLayer to Clamp
* rename ClampLayer to Clamp
Co-authored-by: nbei <631557085@qq.com>
2020-12-09 10:28:32 +08:00
dfa36dfe3b
Merge pull request #652 from dreamerlin/3d
...
[Feature] Add 3D support in wrapper
2020-11-20 16:33:54 +08:00
ec43b671ab
[Enhance]enhance hsigmoid ( #657 )
...
* enhance hsigmoid
* delete int
2020-11-19 21:26:26 +08:00
e70dca8f86
add conv3d
2020-11-18 21:24:20 +08:00
144e7567a7
use pytest.mark.parametrize
2020-11-18 15:35:21 +08:00
86d9f4684a
add MaxPool3d
2020-11-15 19:07:46 +08:00
8ccea20234
add ConvTranspose3d
2020-11-15 18:56:02 +08:00
03214fd446
Support pytorch 1.7 and update the CI ( #631 )
...
* support pytorch 1.7 and update the CI
* fix CI
* fix onnxruntime version in macos
2020-10-31 17:58:15 +08:00
005c408748
Fix wrappers version comparison ( #602 )
...
* add version check in wrappers
* fix assersion
* use digital version for version comparison
* fix unit tests
* reformat
* fall back to compare the first two version
* fix unittest
* fix unittest
* fix unit test
* clean unnecessary change
2020-10-06 12:44:56 +08:00
acee61d7c5
register deconv in CONV_LAYERS ( #582 )
...
* register deconv in CONV_LAYERS
* use ConvTranspose2d implemented in MMCV
* remove repetitive register_module
* update
* add unittest for deconv
2020-09-27 17:51:00 +08:00
c937d3953d
Mv wrappers into bricks and use wrappers in registry ( #550 )
...
* Mv wrappers into bricks and use wrappers in registry
* resolve import issues
* fix import issues
* set nn op forward to torch 1.6.1
* fix CI bug and add warning
* Fix CI by using patch mock
* mv warnings inside deprecated module's initialization
2020-09-12 21:59:17 +08:00
49e32c2688
Implementation of 2D convolution in tensorflow with `padding` as "same" ( #529 )
...
* update impad
* fix docstring
* add shape for impad
* fix unit test
* remove old version & fix doc
* fix linting
* fix doc
* add linear decay learning rate scheduler
* fix impad
* fix setup.cfg
* fix linting
* add yapf
* add swish
* fix lr_updater
* fix lr_updater.py
* update swish
* add swish
* fix inplace
* fix typo
* update
* add same padding
* fix docstring
* add unittest
* fix register
* change name
Co-authored-by: lixiaojie <lixiaojie@sensetime.com>
2020-09-09 23:57:48 +08:00
c3d8eb34ff
add Swish activation ( #522 )
...
* update impad
* fix docstring
* add shape for impad
* fix unit test
* remove old version & fix doc
* fix linting
* fix doc
* add linear decay learning rate scheduler
* fix impad
* fix setup.cfg
* fix linting
* add yapf
* add swish
* fix lr_updater
* fix lr_updater.py
* update swish
* add swish
* fix inplace
* fix typo
Co-authored-by: lixiaojie <lixiaojie@sensetime.com>
2020-08-27 00:39:17 +08:00
56e71a718b
Add Depthwise Seperable ConvModule ( #477 )
2020-08-09 17:29:02 +08:00
6ece0e5d19
Add pairwise function for 'gaussian' and 'concatenation' mode in NonLocal. ( #424 )
...
* add pairwise function for 'gaussian' and 'concatenation' mode
* rename test function
* decrease the complexity of nonlocal unittest
* fix typo and make unittest more complete
* add unittest when zero_init is False
* minor fix
* pack theta and phi
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
2020-07-17 23:44:50 +08:00
7cfc839ea5
Add MMSyncBN in registry ( #420 )
...
* Add MMSyncBN in registery
* skip mmsyncbn test
2020-07-15 19:23:09 +08:00
926ac07bb8
Move fuse conv bn to mmcv ( #382 )
...
* move fuse conv bn to mmcv
* update doc
* update test conv bn
* rename
* fix doc and variable name
* change func name
2020-07-08 19:03:15 +08:00
Zhongyu Li
Shanghua Gao
Zaida Zhou
takuoko
Mashiro
pc
Wenhao Wu
RangiLyu
Jiazhen Wang
Shilong Zhang
Tong Gao
young
Jerry Jiarui XU
Jintao Lin
Miao Zheng
Guangchen Lin
BigBigDream
Rui Xu
Wenwei Zhang
yamengxi
Kai Chen
GT9505
Xiaojie Li
Jintao Lin
Cao Yuhang