Commit Graph

802 Commits (04daea425bcb0a104d8b4acbbc16bd31304cf168)
 

Author SHA1 Message Date
ZhangShilong 03491ed28a
[Enhancement]: add more detail of warning in basemodule (#899) 2021-03-29 11:37:03 +08:00
zhouzaida 75d907c9d1
Bump version to v1.3.0 (#910)
* Bump version to v1.3.0

* Update README.md

* Update README_zh-CN.md
2021-03-28 14:04:24 +08:00
LXXXXR 8647b9a1b1
[Feature] Add cutout and lighting (#909)
* add cutout

* add adjust_lighting

* minor fix
2021-03-26 18:58:19 +08:00
Miao Zheng 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
ZhangShilong a9803da10b
[Feature]: Add transformer base class (#892)
* add transformer base class

* fix according to commments

* resiger module

* change to use basemodule

* add _ between build function

* split the name
2021-03-25 21:31:50 +08:00
Miao Zheng 5f5e8e83c2
[Refactoring] Add Caffe2Xavier Initializer (#902)
* [Refactoring] Add Caffe2Xavier Initializer

* fix lint
2021-03-24 13:25:36 +08:00
Rui Xu 933b052d95
[Feature] Add cuda ops: UpFirDn2d and fused_bias_leakyrelu (#900)
* add upfirdn2d op

* fix bug in pybind

* add fused bias leakyrelu

* fix bug in fused-bias-leakyrelu

* fix lint error

* fix bug in build cpu version

* fix bug in build cpu version

* fix lint

* fix comment from zww

Co-authored-by: zhangshilong <zhangshilong@sensetime.com>
2021-03-21 21:23:09 +08:00
ZhangShilong 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
zhouzaida 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
Miao Zheng 00870b9c4e
[Refactoring] Revise function of is_init flag in BaseModule (#898) 2021-03-18 20:52:45 +08:00
Miao Zheng 967d9d5812
[Refactoring]Add Sequential with init_weight (#884)
* [Refactoring]Add BaseSequtial with init_weight

* revise according to comments

* revise comments

* minors

* baseseq2seq

* add modulelist

* revise minors

* fix isort

* format
2021-03-17 15:45:28 +08:00
sshuair 73bff4ead1
add tifffile backend support for image io (#868)
* add tifffile backend support for imageio

* add tifffile package for test requirements

* add tifffile package for test requirements

* small tiffile
2021-03-12 10:28:30 +08:00
q.yao 9ba1f76005
[Feature] : Add Deformable Conv2d TensorRT Plugin (#858)
* add dcn tensorrt plugin

* prepare for fp16 support

* fix for lint

* limit column buffer

* add docstring to memcpyPermute
2021-03-11 15:41:47 +08:00
ZhangShilong 57f3a6142f
fix scatter in pytorch18 (#882)
* fix scatter in pytorch18

* remove blanks
2021-03-11 13:13:31 +08:00
ZhangShilong 6fc6f75a76
use ubuntu-18.04 in ci (#883) 2021-03-10 12:51:44 +08:00
LXXXXR a4bb2c5b04
[Feature] Support auto contrast (#881)
* support auto contrast

* add comments

* Fix unittest for pillow 6.2.2

* revised according to comments
2021-03-09 18:46:35 +08:00
RunningLeon 3dd98daaa2
fix test unit of nms and batched_nms for tensorrt (#872) 2021-03-08 16:57:19 +08:00
LXXXXR ce10425d2f
[Feature] Add adjust sharpness (#864)
* add adjust sharpness

* revised according to commnts

* fix bug

* fix docstring

* revise according to comments

* fix blank lines

* revised according to comments
2021-03-08 10:23:49 +08:00
LXXXXR 27e9ede5b9
[Fix]: fix bugs in some photometric transforms (#863) 2021-03-03 18:58:15 +08:00
sshuair 6719cde43a
add HTTP backend (#860)
* add HTTP backend

* add HTTPbackend

* fix linting

* fix linting

* add docs attributes http

* fix format

* add real http link test for http backend
2021-03-03 16:23:04 +08:00
Ycr e076c8b042
[Feature] Support revise_keys in load_checkpoint(). (#829)
* Simplified the code.

* Improved chkpt compatibility.

* One may modify the checkpoint via adding keywords.

* Tiny.

* Following reviewer's suggestion.

* Added unit_test.

* Fixed.

* Modify the state_dict  with  construction.

* Added test.

* Modified。

* Mimimalised the modification.

* Added the docstring.

* Format.

* Improved.

* Tiny.

* Temp file.

* Added assertion.

* Doc string.

* Fixed.
2021-03-03 10:59:11 +08:00
Jerry Jiarui XU 34b552b881
[Feature] Support save last checkpoint (#853)
* [Feature] Support save last checkpoint

* move to before_run, update doc

* move to after train

* add comments
2021-02-28 12:50:17 +08:00
Jintao Lin e5eaf2a729
update video/io.py (#856) 2021-02-27 10:28:39 +08:00
z55250825 48d9902585
Add new parrots extension implementation for all ops (#794)
* delete all parrots file
add bbox_overlaps new parrots op impl

* support first new impl parrts op (bbox_overlaps)(success test)

* add box_iou_rotated op, test succeed

* add carafe and carafe_naive op, test succeed (one parrots bug need fix)

* add cc_attention op, test success

* add corner_pool op, test success

* add parrots op deform_conv, test success

* add deform_roi_pool op, test success (but has question)

* add focal loss op, test success (gradcheck)

* add masked_conv2d op, test success

* add modulated_deform_conv op, test success

* add nms and nms_rotated op, test success

* add psamask op, test success

* add roi_align op, test_success

* add roi_pool op, test success

* add sync_bn op, test success

* add tin_shift op, test success

* fix test_deform_roi_pool, add parrots test

* skip test_onnx because parrots does not support onnx

* fix c++ lint

* fix python lint

* fix python lint
2021-02-26 19:05:25 +08:00
RunningLeon 72e4cc12bd
Fix pytorch2onnx failed for interpolate op with PyTorch==1.6.0(mmdet#4646) (#848)
* Fix pytorch2onnx for yolov3 with torch==1.6.0

* update and add test for F.interpolate

* add test_onnx.py with build_cuda
2021-02-26 10:49:12 +08:00
Haian Huang(深度眸) 58a8483352
Fix the iter error when the number of GPUs is different during resume (#844)
* Fix the iter error when the number of GPUs is different during resume

* Add fromstring and unit test

* Remove is_pretty_text

* Fix comment

* Add log info

* Add py format check

* Remove SyntaxError check
2021-02-25 16:40:06 +08:00
Miao Zheng ba30d98a7b
Add docstring for DistSamplerSeedHook (#850) 2021-02-24 10:07:46 +08:00
Jintao Lin 823b62ed94
Fix typo in README (#852) 2021-02-24 10:07:18 +08:00
q.yao 1ee5315ea2
[Feature] : Add NonMaxSuppression TensorRT Plugin (#787)
* start trt plugin prototype

* Add test module, modify roialign convertor

* finish roi_align trt plugin

* fix conflict of RoiAlign and MMCVRoiAlign

* fix for lint

* fix test tensorrt module

* test_tensorrt move import to test func

* add except error type

* add tensorrt to setup.cfg

* code format with yapf

* fix for clang-format

* move tensorrt_utils to mmcv/tensorrt, add comments, better test module

* fix line endings, docformatter

* isort init, remove trailing whitespace

* add except type

* fix setup.py

* put import extension inside trt setup

* change c++ guard, update pytest script, better setup, etc

* sort import with isort

* sort import with isort

* move init of plugin lib to init_plugins.py

* add scatternd, nms plugin (WIP)

* fix bugs of trt_nms

* add trt nms test module

* fix bugs of scatternd

* code optimize, add comment about nms kernel

* fix transform_if bug of trt_nms_kernel

* fix struct name

* default nms offset=0, fix bugs of batched input

* format with clang-format

* onnx preprocess

* much better nms implementation, no need to transfer memory between host and device

* update preprocess_onnx

* parse constant tensor from initializer in preprocess_onnx

* update nms

* remove unnecessary codes

* workspace aligned address

* format trt_plugin_helper.hpp

* fix index memory bugs

* set alignment to 16 by default

* fix lint

* fix nms offset

* fix bugs of preprocess onnx

* update test for nms

* tensorrt only accept int32, not int64

* update nms comments

* fix indexing for scores in nms

* update trt temp

* make trt-nms compatiable to #803

* fix lint

* add docstring to trt_nms_kernel.cuda, add description to preprocess_onnx

* add comment to score indexing

* fix bugs of max output boxes

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-02-23 15:09:49 +08:00
ftbabi 8735815a0d
Add GELU activation function (#843)
* Support GELU activation function

* Support different torch version

* Fix bug in importing TORCH_VERSION

* Wrap GELU module for PyTorch 1.3.x

* Wrap GELU module for PyTorch 1.3.x
2021-02-22 10:55:42 +08:00
Kai Chen b2ffab1306
[feature] Add readme of chinese version (#846)
* add readme of chinese version

* add contribution guide
2021-02-21 21:24:53 +08:00
ftbabi 9637bcff7c
Fix document in cnn.md (#841) 2021-02-21 11:13:39 +08:00
Y. Xiong ca47ae1f87
Bump version to v1.2.7 (#842) 2021-02-20 17:57:05 +08:00
Miao Zheng 72e13e6a0b
fix baserunner bug (#840)
* fix baserunner bug

* add unit test

* hooks type check
2021-02-20 12:46:40 +08:00
Miao Zheng 7fa78e7a1c
add register_itertimer_hook function (#838)
* add register_itertimer_hook function

* set default value

* revise minors

* revise according to comments

* fix according to comments

* update

* update
2021-02-20 10:46:31 +08:00
Zhiyuan Chen f75a88c297
fix no torch.no_grad decorator for val in iter_based_runner (#835) 2021-02-18 22:02:11 +08:00
Wang Xinjiang 3d229dbaf2
Add more error info in build_from_cfg (#834)
* Add more Error info in building from config

* Add more Error info in building from config

* change error info
2021-02-18 13:07:42 +08:00
lizz 1c2e665ad6
map_location for all (#826)
* map_location for all

* format

* hmm

* map_location

* back

* doc

* same
2021-02-10 12:23:39 +08:00
Miao Zheng 999f2d08b4
fix weight_init.py (#825)
* fix weight_init.py

* revise BaseInit args
2021-02-07 17:24:03 +08:00
ZhangShilong 4712db75d6
Fix bug of DCN (#819)
* fix bug of DCN

* fix clang=format
2021-02-07 13:05:27 +08:00
Miao Zheng 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
Luting Wang 11b9264053
fix: imshow_bboxes fails with incontiguous img (#823) 2021-02-07 11:10:42 +08:00
lml131 4a694cc0ee
add PARROTS_JIT_OPTION (#816)
* code update

* add PARROTS_JIT_OPTION

* rm flow_warp_module

* fix for lint

* small fix
2021-02-05 19:58:33 +08:00
RunningLeon 5df759ad44
[Fix]: add header file for std::iota(#803) (#820)
* add header to std::iota

* fix lint

* fix lint for cpp
2021-02-05 12:52:19 +08:00
RunningLeon 459d728c47
[Fix]: parse scales of list in PyTorch==1.7.0 (#451 in MMPose) (#815)
* modify symbolic

* add comments
2021-02-04 15:47:19 +08:00
tangyanf be2616a0e2
add ort nms op (#803)
* add ort nms op

* fit lint check

* fix lint check

* update code

* fix lint check

* update code

* update code

* update code

* update code

* update code

* update code
2021-02-04 15:45:09 +08:00
ftbabi 6c57b88f5d
Fix document in io.md (#813) 2021-02-02 22:50:18 +08:00
Rui Xu cf2f14d06c
[Feature] Add file mode for logger (#808)
* add file mode for logger

* add more docs and comments
2021-02-02 22:49:24 +08:00
Jintao Lin 93980b4b91
[Docs] Polish CONTRIBUTING for all OpenMMLab projects (#807)
* polish CONTRIBUTING for all OpenMMLab projects

* polish some description
2021-02-01 15:38:03 +08:00
RunningLeon 5afca135f7
[Doc]: add a short document for TensorRT plugins in mmcv (#797)
* add trt doc

* add notes

* add sphinx_markdown_tables

* resolve comments

* resolve comments
2021-01-28 15:57:13 +08:00