Commit Graph

298 Commits (b55bf8ec1b5b67b7ddcab149b1f197cb4b677521)
 

Author SHA1 Message Date
lvhan028 b55bf8ec1b
[Docs] update acknowledgement and MMDeploy's short introduction (#15)
* add mmdeploy short introduction

* add acknowledgement to OpenPPL team

* update acknowledgement
2021-12-29 19:24:03 +08:00
AllentDan f693f7cc41
[Enhancement] support coverage (#16)
* support coverage

* test codecov action 2
2021-12-29 16:26:41 +08:00
RunningLeon f2594c624b
add openvino.md to index.rst (#11) 2021-12-27 20:21:08 +08:00
AllentDan 26d40fe883
fix (#10) 2021-12-27 13:45:35 +08:00
q.yao 466ed64739
update links (#9)
* update links

* remove link
2021-12-27 13:01:27 +08:00
lzhangzz 454d7fdc46
remove csrc/README.md (#8) 2021-12-27 11:35:25 +08:00
q.yao 428ef05c07
[Other] Update readme tags (#6)
* correct url.

Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>

* Add readme tags

Co-authored-by: lvhan028 <lvhan_028@163.com>
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
2021-12-27 11:20:26 +08:00
AllentDan 3a8b9837ce
Url (#7)
* fix url Co-authored-by: maningsheng@sensetime.com

* fix url

Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com>

* fix url

Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: del-zhenwu <56623710+del-zhenwu@users.noreply.github.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com>

Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: del-zhenwu <56623710+del-zhenwu@users.noreply.github.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com>
2021-12-27 11:08:21 +08:00
AllentDan cfd41d03e2
add ncnn latency benchmark to zh_cn (#5) 2021-12-27 10:20:15 +08:00
lvhan028 d8d3c354c3
correct url. (#4)
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>

Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
2021-12-24 22:16:23 +08:00
q.yao f4e152098b
update bug-report (#1)
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>

Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-24 21:39:14 +08:00
lzhangzz 1a35cf85b4
fix intro (#337) 2021-12-24 18:49:09 +08:00
lvhan028 d79413fa32
update c-api's comments by following doxygen's guide (#336)
* update c-api's comments by following doxygen's guide

* fix according to review comments
2021-12-24 18:43:26 +08:00
VVsssssk 09f14fa4b7
[Docs]Remove cn docs (#335)
* remove cn docs

* fix index.rst

* fix index.rst
2021-12-24 18:14:45 +08:00
VVsssssk 15bdafed1f
[Docs]Add a support model list. (#333)
* add docs about support model

* fix docs

* fix support list

* fix docs

* fix format

* fix how to convert model

* fix en and cn docs about convert model

* fix bash

* fix docs format

* fix readme

* fix benchmark

* fix cn docs link

* rename support models

* rename

* fix docs

* fix cn benchmark

* fix benchmark
2021-12-24 17:20:06 +08:00
q.yao 02e033ba5b
[Docs] Add zh_cn get_started (#327)
* start up

* zh-cn v0.1

* [Docs] Add a from-scratch example for "Get Started" (#326)

* Add a from-scratch example

* Fix typo

* resolve comment

* bachslash

* Resolve comments

* Refine commands

* add cn docs

* Correct commands

* fixing...

* update zn-cn docs

* update en link

* add sdk's get-started (#331)

* add sdk's get-started

* add SDK build command

* fix chinglish

* add sdk get start zh_cn

* update zh_cn cite

* fix command

* add selfsup/razor readme

* Fix command

Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-24 15:26:50 +08:00
hanrui1sensetime 8e19a08bcf
[Doc] Add other ncnn ops docs. (#329)
* add other ops

* fix comments

* add ncnn.md

* remove gpu
2021-12-24 14:27:03 +08:00
hanrui1sensetime e355aad45f
[Docs] add ncnn latency benchmark (#314)
* WIP add benchmark.md

* add mmocr already

* add retina

* add mask rcnn none

* update mmdet benchmark

* fill mmcls benchmark

* add mmocr and mmedit

* add some mmseg benchmark of cpu

* add all data

* add platform

* remove mmseg mmedit ncnn and dbnet ncnn

* fix grammar typo

* fix comments

* fix typo
2021-12-24 10:39:31 +08:00
lzhangzz 4bb37c54a2
Fix logo and intro (#334)
* crop logo

* fix README_zh-CN.md

* remoe empty files
2021-12-23 20:14:35 +08:00
VVsssssk e37ce3cf28
[Doc]: MMDet benchmark (#265)
* add mmdet benchmark

* fix docs

* fix docs

* fix docs

* add fp16

* add some int8 model

* add yolov3 benchmark

* add some benchmark

* fix docs

* add comment about mask-rcnn

* fix mmdet docs

* add ppl benchmark

* refactor benchmark

* refactor format

* add fcos and atss fp16

* fix benchmark

* fix mmdet docs

* fix docs

* fix docs

* fix docs

* add cn benchmark about mmdet
2021-12-23 17:42:14 +08:00
VVsssssk fce37d4594
【Docs】Fix docs about codebase (#317)
* fix codebase docs

* fix edit

* fix mmcls docs

* fix docs
2021-12-23 17:35:59 +08:00
VVsssssk f6dcd390e1
fix ops unit test (#332) 2021-12-23 16:43:30 +08:00
lvhan028 175d024dd9
check in introduction image (#328) 2021-12-23 16:18:16 +08:00
RunningLeon 49b47ff614
[Doc]: Add build doc of CN (#323)
* update build cn

* update

* add introduction to build sdk

* add note

* update doc

* remove unused html tag

Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-23 16:10:04 +08:00
lvhan028 cdd0cf0988
[Docs] add sdk's build instructions (#324)
* add sdk's build instructions

* update according to review comments
2021-12-23 14:54:56 +08:00
lvhan028 98da5e8ba4
use wrong core's directory when install c++ header files (#330) 2021-12-23 14:31:17 +08:00
RunningLeon f76ac64cfe
update backend docs (#319) 2021-12-23 13:23:39 +08:00
VVsssssk 9d4d52078b
【Fix】Fix ppl bug about grid sample (#325)
* fix ppl problems

* fix roialign

* fix grid_sampler bug

* fix grid sampler

* fix config

* fix test
2021-12-23 12:11:07 +08:00
AllentDan 199253ce94
[Doc] Refine benchmark (#318)
* add to index

* fix link

* add chinese benchmark

* add openvino to backends

* add codebase name

* add benchmark to bechmark model zoo

* update chinese mmcls benchmark
2021-12-23 11:25:45 +08:00
AllentDan 493caabf7b
[Docs] Refine chinese readme (#322)
* refine chniese readme

* fix lint

* update logo, features and acknowledgement

* add qrcode url

Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-22 19:07:10 +08:00
hanrui1sensetime 9e22c75b70
[Docs] add ncnn ops docs samples (#313)
* add ncnn ops docs samples

* link ops to ncnn.md

* fix ncnn.md grammar

* fix grammar typo
2021-12-22 15:50:11 +08:00
q.yao 7bfe1ad886
fix instance-norm tensorrt plugin (#321) 2021-12-22 10:46:03 +08:00
Yifan Zhou 543777fe27
[Docs] Update mmcls pplnn benchmark (#316)
* Update mmcls pplnn benchmark

* Update supported model list
2021-12-22 10:43:39 +08:00
lvhan028 e10a1b7c9e
Add more demos (#305)
* add more examples

* change to restore's output image to BGR

* use BUILD_SHARED_LIBS

* update graph module's cmake

* add condition for spdlog package

* change cmakelists

* update cmakelists

* add device_name in each demo

* remove duplicate cmake function

* use palette to draw segmentation's result

* no need to find_package(pplnn) when use MMDeploy's static libs

* remove MMDeploy_LIBS' dependency on spdlog

* #include <opencv2/imgproc/imgproc.hpp>

* change from mmdeploy_core to mmdeploy::core
2021-12-21 21:32:39 +08:00
lzhangzz 56e32fdf63
improve shape checking (#315) 2021-12-21 20:16:40 +08:00
VVsssssk ce2b778061
[Fix]: fix pplnn empty output error (#320)
* fix ppl problems

* fix roialign
2021-12-21 19:49:06 +08:00
hanrui1sensetime 33bde90744
[Fix] Fix unittest of ncnn. (#309)
* fix test_pytorch_functions

* fix test_mmocr_models
2021-12-21 18:03:50 +08:00
Yifan Zhou c1ed41c465
[Docs] Refactor document structure (#310)
* Refactor docs

* Fix path

* Update logo
2021-12-21 13:59:07 +08:00
RunningLeon b060908a58
fix ut (#311) 2021-12-21 11:56:51 +08:00
lzhangzz 43e6714f47
[SDK] Fix asan errors (#308)
* fix several heap-use-after-free bugs

* rebase master

* add option for sanitizers

* rebase master

* fix conflicts
2021-12-21 10:47:21 +08:00
AllentDan 547a160770
Fix cub (#312)
* fix cub path

* use cmake source dir instead
2021-12-20 21:01:32 +08:00
RunningLeon d9b23bfc6f
[fix]: get tensor for DataContainer case (#307)
* fix DataContainer case for get_tensor_from_input

* fix docstring
2021-12-20 19:49:44 +08:00
Yifan Zhou 0f9f0a60e4
[Enhancement]: Update configs for OpenVINO (#306)
* Update config for OpenVINO

* Update test

* Update better test

* Update instance-seg config of OpenVINO
2021-12-20 17:56:25 +08:00
q.yao abdf64a576
[Fix] support ncnn faster-rcnn (#304)
* wtf

* Support fcos ncnn end2end

* support ncnn two stage detector

* fix test
2021-12-20 15:43:38 +08:00
RunningLeon fabdb473bb
Update ncnn test (#298)
* update ncnn test

* type hint

* update test ocr

* update mmseg ut

* ignore ncnn rpn head test

* add logging

* fix ssd base dense head test

* recover bacth in ncnn wrapper

* fix ncnn_ops_ut

* fix yapf

* recover test ops

* fix run_with_backend False

* Revert "fix run_with_backend False"

This reverts commit 83f8f915a25e800f5c2db339584d164ba40b2d9b.

* disable ncnn test test_pytorch_functions.py

Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
Co-authored-by: hanrui1sensetime <hanrui1@sensetime.com>
2021-12-20 14:05:13 +08:00
q.yao 270d98a8a2
[Fix] Support ncnn fcos end2end export (#303)
* wtf

* Support fcos ncnn end2end
2021-12-20 12:12:02 +08:00
RunningLeon ab5c51f3ab
fix mmdet tests (#302)
* fix mmdet tests

* fix
2021-12-18 14:36:54 +08:00
lvhan028 3be1779e66
Refactor tests (#283)
* fix sdk model's pipeline.json

* resize INT64 mask

* refactor unit tests

* fix api in model.h

* remove 'customs' from meta info

* fix zip model

* fix clang-format issue

* put tc on each backend into a SECTION

* change SECTION title

* add DYNAMIC_SECTION for capi unit test

* change 'devices' to 'device_names'

* change trt to tensorrt

* remove uncessary check

* add color_type 'color_ignore_orientation' which is used in ocr

* 'min_width', 'max_width' and 'backend' might be null in pipeline config

* fix clang-format issue

* remove useless code
2021-12-17 19:57:37 +08:00
AllentDan d3e8473f87
fix ci (#301)
* show mmcv

* test

* repalce

* refine
2021-12-17 14:30:11 +08:00
q.yao 75a9ffa611
fix ncnn linear (#299)
* fix ncnn linear

* lstm rewriter

* fix lint

* add comment
2021-12-17 14:12:37 +08:00