Commit Graph

714 Commits (b1df16a409c15ea69519e44d690bf06786f6e970)
 

Author SHA1 Message Date
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
pc 3c7321c00d
[Fix] Fix pybind exporting bug in fused_bias_leakyrelu and upfirdn2d (#1005)
* fix export bug in pybind

* fix type bug in fused_bias_leakyrelu backward
2021-04-29 18:35:11 +08:00
Zaida Zhou ab973df6cd
Bump version to v1.3.2 (#999) 2021-04-27 21:58:44 +08:00
Ziyi Wu 04346fc7d0
[Feature] Support clipping min_lr in StepLrUpdaterHook to help MMDet3D (#995)
* support clipping min_lr in StepLrUpdaterHook

* add docstring for StepLrUpdaterHook

* fix small bugs

* add unit test for StepLrUpdaterHook

* fix linting error
2021-04-27 20:53:29 +08:00
gengenkai f46e5f8e5e
[Fix] Fix add_graph in pavi (#948)
* [Fix] Fix add_graph in pavi

* change data loader to image

* Delete =2.4.0

* pavi-add_graph-0419

* pavi-add_graph-0419

* [Fix] pavi device

* fix device in pavi-add graph

* img_key

* img_key

* add no_grad

* Delete version.py

* add version.py
2021-04-27 19:31:23 +08:00
Zaida Zhou c142eced17
[Feature] Add PyTorch Profiler to analyze training process (#937)
* [Feature] Add PyTorch Profiler to analyze training process

* [Feature] Add PyTorch Profiler to analyze training process

* pring log and fix docstring

* add by_epoch

* modify docstring according to comment
2021-04-27 19:08:09 +08:00
WRH 5d75c7a8ee
[Enhancement]: use len(result) as batch size (#987)
* use len(result) as batch size

* remove old comments

* Add comments to this modification

* Update test.py
2021-04-27 14:04:55 +08:00
Y. Xiong fffc87578f
[Feature]: Support auto_fp16 using torch.cuda.amp when PyTorch >= 1.6.0 (#951)
* add torch.cuda.amp to fp16_utils and optimizers

* use with context manager for autocast

* add doc to explain the behavior differences between real amp and ours

* fix docstring
2021-04-27 13:55:59 +08:00
Wang Xiaolin 0fc19b4692
[Feature]: parrots add parrots/fused_bias & upfirdn2d (#989) 2021-04-27 13:49:50 +08:00
Haian Huang(深度眸) 1738d50c17
Use Sequential rather than nn.Sequential in build_model_from_cfg. (#992) 2021-04-27 13:43:59 +08:00
Rui Xu 0be0410443
[Bug] fix raise error bug in registering multiple names (#949)
* fix raise error bug in registering multiple names

* fix bug in checking the type of name

* fix lint

* fix unit test for registry

* fix bug in unit test
2021-04-25 21:47:50 +08:00
Zaida Zhou 478563888e
[Docs] Refactor readme.md (#984)
* [Docs] Refactor readme.md

* use lowercase
2021-04-25 19:25:14 +08:00
WRH 5a99f587ed
[Feature]: support CPU training with MMDataParallel (#972)
* support for CPU training

* Update .pre-commit-config.yaml

* Update data_parallel.py
2021-04-24 21:28:58 +08:00
Rui Xu 841a078e69
[Fix]: fix data type in fused-bias-leakyrelu for apex fp16 training (#981) 2021-04-24 19:10:13 +08:00
whughw 9649a9ad22
Incorrect citation in transformer documentation. (#974) 2021-04-23 17:57:51 +08:00
ZhangShilong 54a7ebb4ec
[Feature]: support Multi-Scale-DeformAttention in deformable-detr (#878)
* add c++ ms_deform_atten

* fix cpp lint

* fix cpp lint

* clang format

* remove cmakefile

* google style

* clang-format precommit

* use clang-format-lint-action

* add transformer base class

* add merge

* add docstr

* add pyargs

* fix according to commments

* resiger module

* change to use basemodule

* add _ between build function

* split the name

* fix according to comments

* fix lint and fix unitest

* fix cpp lint

* fix bug of deformdetr_atten

* fix drop out

* fix residual

* use CUDA_1D_KERNEL_LOOP
2021-04-23 16:35:15 +08:00
Wenwei Zhang 0dd0c49a5b
[Enhancement]: Add issue and PR template (#966)
* add issue and PR template

* rephrase

* fix lint

* resolve comments

* fix typo

* resolve comment
2021-04-22 14:38:42 +08:00
Miao Zheng a76416393c
[Fix] Rename init_weight to init_weights (#971)
* [Fix] Rename init_weight to init_weights

* warning msg
2021-04-20 14:49:42 +08:00
Wang Xinjiang ee041cec6a
[Feature]: Add Rotated ROI align op for pytorch (cpu&cuda), parrots (cpu&cuda) and onnxruntime (cpu) (#933)
* add roi_align_rotated

* code format

* Add align key to roi align rotated

* Add clockwise for rotated roi align

* fix bugs in onnx export

* Add docstring for RoIAlignRotated

* remove cuda unittest

* Reformat c++ code

* add onnx roi align rotated file

* fix unittest

* Add  cpu and float64 of cuda support for parrots

* code format

* Add unified header to roi align rotated

Co-authored-by: luopeichao <luopeichao@sensetime.com>
2021-04-19 15:04:01 +08:00
ZhangShilong de4f14e9cd
[Enhancement]: refactor init cfg (#958) 2021-04-18 22:40:13 +08:00
tangyanf 5504b5fbcf
fix compile without cuda (#945) 2021-04-17 12:16:40 +08:00
ZhangShilong cb0ee1e339
Remove redundant self.init_cfg (#959) 2021-04-17 10:06:44 +08:00
zhouzaida ae411509dd
[Docs] Add QR code in CN README (#954) 2021-04-16 21:22:51 +08:00
zhouzaida 1bc912eb57
Bump version to v1.3.1 (#950) 2021-04-16 10:53:27 +08:00
zhouzaida 54ece10ffb
[Docs] Add mmocr link (#941)
* [Docs] Add mmocr link

* Update README.md

* Update README_zh-CN.md
2021-04-14 20:07:07 +08:00
zhouzaida 47d29795ff
[Fix] Fix train error EpochBasedRunner (#942) 2021-04-14 20:00:20 +08:00
ZhangShilong 8d7e0a6d6a
[Refactor]: add init_cfg in transformer base classes (#946) 2021-04-14 18:04:08 +08:00
Miao Zheng 79f8cbd661
[Bug] Fix DeformConv2d bias error and add tests (#940)
* [Bug] Fix DeformConv2d bias error and add tests

* fix repr

* revise tests

* lint
2021-04-12 20:31:34 +08:00
SFMDI 3bcc796d38
[Fix]: Fix cuda compile error on visual studio 16.9 (#891)
* replace floor/ceil to floorf/ceilf

to eliminate cuda compilation errors in the latest version of Visual Studio 16.9

* fix lint error

* fix lint

* fix lint

* Update .pre-commit-config.yaml

* Update .pre-commit-config.yaml

Co-authored-by: wangruohui <12756472+wangruohui@users.noreply.github.com>
2021-04-12 14:08:21 +08:00
q.yao e478e9ff7f
[Doc]: Add document of TensorRT and onnxruntime custom ops (#920)
* update tensorrt plugin document

* add onnxruntime custom ops document

* format document

* add release note to onnxruntime_op and tensorrt_plugin

* update document

* add deployment.rst

* add grid_sampler onnxruntime document

* fix lint

* add allow_different_nesting tag

* add allow_different_nesting tag

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-04-12 14:06:28 +08:00
Miao Zheng 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
Jerry Jiarui XU 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
Miao Zheng 47825b194e
[Refactoring] Revise init_weight in BaseModule (#905)
* [Refactoring] Add deprecated API warning

* revise test

* fix lint

* fix lint
2021-04-10 21:20:53 +08:00
Miao Zheng 89efc607ef
[Fix] OneCycleLrUpdaterHook adds total_steps (#929)
* [Fix] OneCycleLrUpdaterHook interface

* revise according to comments

* revise according to comments

* add test

* fix lint

* revise according to comments

* minors

* add pytest param

* fix lint

* ci
2021-04-10 21:19:45 +08:00