Sync master into dev-1.x #1091

RunningLeon · 2022-09-22T11:58:31Z

Motivation

Sync master into dev-1.x

Note: Better not to squash merge this PR.

This PR

Modification

Check each conversion, ut, sdk of each codebase

Check special backends

ascend @lzhangzz
rknn @AllentDan
coreml @grimoire

BC-breaking (Optional)

None

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

Pre-commit or other linting tools are used to fix the potential lint issues.
The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
The documentation has been modified accordingly, like docstring or example tutorials.

change `make -install` to `make install` open-mmlab#618

* fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api

…b#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <[email protected]>

* fix shufflenetv2 and pspnet * fix ci * remove print

If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing

same with open-mmlab#654

* support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by open-mmlab#477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci

* Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <[email protected]>

* optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test

* custom trt anchor generator * add ut * add docstring, update doc

* update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs

* add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci

…indows and linux-gpu (open-mmlab#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests

* Add fuse select assign pass * move code to csrc * add config flag * remove bool cast

Fix backend model assignment

* fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later

* resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test

* bump vertion to 0.6.0 * update version

* pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo

* fix ssd ncnn ut * fix yapf

* fix android build * fix cmake * fix url link

* Update result of TextSnake result from https://github.com/BrokenArrow1404/2022-MMLAB-SUMMERCAMP/blob/main/week4/README.md * Update result of TextSnake result from https://github.com/BrokenArrow1404/2022-MMLAB-SUMMERCAMP/blob/main/week4/README.md * Add deploy config for quantization of TextSnake * repair lint error

add mim update circle ci fix tests fix ci

* fix mmcls cifar10 config * fix dump-info for cifar10 config * use regex instead of packlist * remove constants unused * fix while logic * fix lint * fix docformatter * fix classification to avoid conflict

…pen-mmlab#1068) (open-mmlab#1093)

* fix(tools/profile.py): rename to avoid name conflict * fix(docs): remove useless

* ocr/short_scale_aspect_jitter.cpp scale_factor double to float not working on c++11 * ocr/short_scale_aspect_jitter.cpp scale_factor double to float not working on c++11 * ocr/short_scale_aspect_jitter.cpp scale_factor double to float not working on c++11 add install mmengine in docker file * 1. ocr/short_scale_aspect_jitter.cpp scale_factor double to float not working on c++11 2. add install mmgine in dockerfile 3. add install_mmengine in circleci * fix mmengine typo

fix ci and lint fix det fix cuda ci fix mmdet test update object detection fix ut fix layer norm ut update ut lock mmeit version fix mmocr mmcls ut add conftest.py fix ocr ut fix mmedit ci install mmedit from source fix rknn model and prepare_onnx_paddings__tensorrt UT docstring fix coreml export update mmocr config small test recovery assert fix ci

* update doc about mmclassfication deployment * update install mmdeploy part * correct mmcls deployment commands * reformat supported models * add deployed model specification * update doc about mmdetection deployment * fix according to reviewer comments * fix according to reviewer comments * fix according to reviewer comments * fix according to reviewer comments * fix according to reviewer comments * fix according to reviewer comments * update doc about mmsegmentation deployment * update doc about mmocr deployment * check in cityscapes.png as an input image for converting mmsegmentation model * update mmocr deployment * update mmseg.md * update mmseg.md * update mmocr.md * update sdk model inference for mmocr deployment * update according to reviewer comments * update * update * update mmedit * update mmpose deployment * check in face.png for mmedit deployment * update * fix according to reviewer comments * remove duplicate doc * update docs in english * update codebase documents in chinese * fix according to reviewerss comments * update according reviewer comments * ObjectDetection -> Object Detection * InstanceSegmentation -> Instance Segmentation

* support for external codebase like mmyolo * support for external export * fix missing flake8 * fix comments * add aenum * add missing files * fix condition * refactor import_codebase * fix mmyolo support * fix lint * add base codebase * fix a strange clang-format * fix import_codebase * fix dependent codebase register * wrap custom_model * fix comment * add ut

codecov · 2024-08-16T21:01:28Z

Codecov Report

Attention: Patch coverage is 20.50781% with 1221 lines in your changes missing coverage. Please review.

Project coverage is 46.50%. Comparing base (1da5464) to head (da1204d).
Report is 312 commits behind head on dev-1.x.

Files	Patch %	Lines
mmdeploy/backend/ascend/wrapper.py	0.00%	332 Missing ⚠️
mmdeploy/backend/sdk/tracer.py	0.00%	99 Missing ⚠️
mmdeploy/backend/coreml/torchscript2coreml.py	0.00%	58 Missing ⚠️
mmdeploy/codebase/mmcls/models/utils/attention.py	10.71%	50 Missing ⚠️
mmdeploy/codebase/mmdet/models/layers/bbox_nms.py	16.94%	49 Missing ⚠️
...det/models/roi_heads/single_level_roi_extractor.py	14.03%	48 Missing and 1 partial ⚠️
mmdeploy/backend/coreml/ops.py	0.00%	45 Missing ⚠️
mmdeploy/backend/ascend/onnx2ascend.py	0.00%	42 Missing ⚠️
mmdeploy/backend/rknn/onnx2rknn.py	0.00%	39 Missing ⚠️
mmdeploy/backend/tensorrt/utils.py	0.00%	38 Missing ⚠️
... and 49 more

Additional details and impacted files

@@             Coverage Diff             @@
##           dev-1.x    #1091      +/-   ##
===========================================
- Coverage    49.51%   46.50%   -3.01%     
===========================================
  Files          306      305       -1     
  Lines        10801    10807       +6     
  Branches      1617     1567      -50     
===========================================
- Hits          5348     5026     -322     
- Misses        5067     5408     +341     
+ Partials       386      373      -13

Flag	Coverage Δ
unittests	`46.50% <20.50%> (-3.01%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

DrRyanHuang and others added 30 commits June 20, 2022 14:46

make -install -> make install (open-mmlab#621)

9c8168f

change `make -install` to `make install` open-mmlab#618

[Fix] fix csharp api detector release result (open-mmlab#620)

f30eacf

* fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api

Reduce mmcls version dependency (open-mmlab#635)

ae47e9d

fix shufflenetv2 with trt (open-mmlab#645)

fa034e0

* fix shufflenetv2 and pspnet * fix ci * remove print

' -> " (open-mmlab#654)

49608b4

If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing

' -> " (open-mmlab#655)

7e8d6eb

same with open-mmlab#654

simplify Expand (open-mmlab#617)

82a74d8

Fix typo (open-mmlab#625)

05cafab

* Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <[email protected]>

[Enhancement] Fix ncnn unittest (open-mmlab#626)

4d9e209

* optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test

[Enhancement] TensorRT Anchor generator plugin (open-mmlab#646)

dc5f9c3

* custom trt anchor generator * add ut * add docstring, update doc

update docs (open-mmlab#624)

5fce1e8

update the circleci config file by adding workflows both for linux, w…

30d62e9

…indows and linux-gpu (open-mmlab#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests

Fixed tensorrt plugin not found in Windows (open-mmlab#672)

0f0f676

update introduction.png (open-mmlab#674)

b1f156a

[Enhancement] Add fuse select assign pass (open-mmlab#589)

5858488

* Add fuse select assign pass * move code to csrc * add config flag * remove bool cast

fix export sdk info of input shape (open-mmlab#667)

c792d06

Update get_started.md (open-mmlab#675)

3bc766e

Fix backend model assignment

Update get_started.md (open-mmlab#676)

e49e8a1

Fix backend model assignment

[Fix] fix clang build (open-mmlab#677)

8f1508e

* fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later

Deploy the Swin Transformer on TensorRT. (open-mmlab#652)

efd3995

* resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test

bump version to 0.6.0 (open-mmlab#680)

5195ff9

* bump vertion to 0.6.0 * update version

pass img_metas while exporting to onnx (open-mmlab#681)

17a7d60

* pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo

[Fix] fix ssd ncnn ut (open-mmlab#692)

affc5ae

* fix ssd ncnn ut * fix yapf

fix passing img_metas to pytorch2onnx for mmedit (open-mmlab#700)

029ed69

fix passing img_metas for mmdet3d (open-mmlab#707)

69c38b9

[Fix] Fix android build (open-mmlab#698)

d57cf85

* fix android build * fix cmake * fix url link

BrokenArrow1404 and others added 3 commits September 21, 2022 15:28

fix layer norm (open-mmlab#1015)

ea7706c

Merge master:ea7706cb into sync_master

40adb32

RunningLeon added the WIP label Sep 22, 2022

RunningLeon and others added 11 commits September 29, 2022 16:26

fix github ci

144fcf7

add mim update circle ci fix tests fix ci

[Fix] Fix mmcls for cifar10 config on dev-1.x (open-mmlab#1056)

89a9e92

* fix mmcls cifar10 config * fix dump-info for cifar10 config * use regex instead of packlist * remove constants unused * fix while logic * fix lint * fix docformatter * fix classification to avoid conflict

improvement(ubuntu_utils.py): check upstream libopencv-dev version (o…

a53ffec

…pen-mmlab#1068) (open-mmlab#1093)

fix(tools/profile.py): rename to avoid name conflict (open-mmlab#1087)

2f7e61c

* fix(tools/profile.py): rename to avoid name conflict * fix(docs): remove useless

remove deploy test loop and enable edit SDK (open-mmlab#1083)

c0ae726

fix mmedit 2.0 dump info for sdk (open-mmlab#1120)

b8c19b3

remove threshold

db2c512

RunningLeon force-pushed the sync_master branch from e6c9ef2 to db2c512 Compare September 29, 2022 08:43

RunningLeon requested review from grimoire, lzhangzz and lvhan028 September 29, 2022 09:30

RunningLeon force-pushed the sync_master branch 2 times, most recently from 657d11f to 18b175b Compare September 29, 2022 10:23

RunningLeon removed the WIP label Sep 29, 2022

fix conflicts with dev-1.x

b78121a

RunningLeon force-pushed the sync_master branch 2 times, most recently from 3d73e7d to d2cc610 Compare September 30, 2022 10:26

Update CI to only use python -m

da1204d

RunningLeon force-pushed the sync_master branch from d2cc610 to da1204d Compare September 30, 2022 10:45

RunningLeon merged commit 8bae567 into open-mmlab:dev-1.x Oct 8, 2022

grimoire mentioned this pull request Sep 26, 2024

[Bug] Error Exporting RetinaNet for Single Class Case with CrossEntropyLoss in MMDeploy #2787

Closed

3 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Sync master into dev-1.x #1091

Sync master into dev-1.x #1091

RunningLeon commented Sep 22, 2022 •

edited

Loading

codecov bot commented Aug 16, 2024 •

edited

Loading

Sync master into dev-1.x #1091

Sync master into dev-1.x #1091

Conversation

RunningLeon commented Sep 22, 2022 • edited Loading

Motivation

Note: Better not to squash merge this PR.

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

codecov bot commented Aug 16, 2024 • edited Loading

Codecov Report

RunningLeon commented Sep 22, 2022 •

edited

Loading

codecov bot commented Aug 16, 2024 •

edited

Loading