Commit Graph

848 Commits (c73756366e374507b5d619cfe06deea72d2ad61d)
 

Author SHA1 Message Date
lvhan028 692f535702
fix side effect caused by PR1235 (#1239) 2022-10-24 14:15:26 +08:00
Xu Lin c82a7ac89e
add MMYOLO desc in README (#1235) 2022-10-24 11:37:11 +08:00
q.yao 4a150e5e1b
update API for TensorRT8.4 (#1144) 2022-10-24 10:52:18 +08:00
AllentDan 114b0b8238
remove imports (#1207)
* remove imports

* update doc

* detailed docstring

* rephrase
2022-10-24 10:45:52 +08:00
lvhan028 4c872a41c3
tell batch inference demos and single image inference demos apart (#986) 2022-10-19 19:42:22 +08:00
LiuYi-Up 27ac0ab002
[Docs] add support for vipnas (#1164)
* add support for vipnas

* add some unit tests

Signed-off-by: LiuYi-Up <1150854440@qq.com>

* Update quantization.md

* resolve some conflicts in docs

Signed-off-by: LiuYi-Up <1150854440@qq.com>

* fix the mdformat

Signed-off-by: LiuYi-Up <1150854440@qq.com>

* fix the layer_norm.py & test_mmcv_cnn.py

Signed-off-by: LiuYi-Up <1150854440@qq.com>

Signed-off-by: LiuYi-Up <1150854440@qq.com>
2022-10-19 10:24:23 +08:00
AllentDan 3eb60ea584
[Feature] Add RKNN support to SDK (#1145)
* add rknn_net [WIP]

* add cmake

* enable mmcls

* remove toTensor in SDK pipeline

* update doc

* translate to Chinese

* update doc and add tool-chain cmake

* use ::framework

* fix lint

* doc and print log

* data map

* refine install doc

* add rknpu2 workflow

* update gcc yaml

* better cmake file

* update doc link

* use vector instead of array

* better env variable

* use soft link

* release ctx

* name rule
2022-10-18 17:52:31 +08:00
Jiahao Sun 8e634059a1
[Feat] Support Monocular 3D Detection and FCOS3D Deployment (#1047)
* add monodet task

* format monodet

* format monodet

* sort test_monocular_detection_model.py import

* add fcos3d deploy

* change doc support model & fcos3d UT

* fix test monodet UT bug & remove ONNXBEVNMS op
2022-10-18 11:23:39 +08:00
q.yao 954e0d2ca1
update symbolic rewriter (#1122)
* update symbolic rewriter

* update ut
2022-10-18 11:21:54 +08:00
RunningLeon b20741352e
update reg (#1217) 2022-10-18 11:16:38 +08:00
OldDreamInWind 161fb01d73
[Feature]add edsr result && super-resolution ncnn-int8 config (#1111)
* add edsr result && ncnn-int8 config

* fix lint error

* fix lint error

* fix lint error && update benchmark.md

* add EDSRx2 pytorch result

* update edsrx4 result in benchmark
2022-10-18 10:04:56 +08:00
SsTtOoNnEe dd7550a08d
Rewrite Conv2dAdaptiveOps for conversion of EfficientNet (static shape) (#1045)
* Rewrite Conv2dAdaptiveOps for conversion of EfficientNet (static shape)

* Refactor codes and Add unit test

* Simplify codes

* update supported model configs in yaml

* update mmcls.yml

* resolve lint error

Co-authored-by: SenseTime Research Singapore <SENSETIME\research.sgres@sg0016000001u.domain.sensetime.com>
2022-10-17 16:20:30 +08:00
lvhan028 1c478393c0
update issue form (#1206)
* update issue form

* udpate issue form

* udpate issue form

* udpate issue form

* udpate issue form
2022-10-17 15:26:02 +08:00
tpoisonooo ace44ae9d9
improvement(scripts): cross build aarch64 (#1126)
* udpate

* update

* CI(scripts): add auto cross build aarch64

* docs(scripts): add zh_cn doc

* docs(scripts): update

* docs(scripts): update

* fix(tools): update

* docs(zh_cn): update

* fix(scripts): remove gcc-7

* docs(scripts): update result

* udpate

* fix(tools): remove useless option

* docs(en): typo

* Update cross_build_aarch64.md

* Update cross_build_aarch64.md

* fix(tools/scripts): review advices

* fix(tools/scripts): update

* fix(cmake): remove useless option

* Update aarch64-linux-gnu.cmake
2022-10-17 11:15:29 +08:00
Mengyang Liu f8551b0316
Fix rust_api CI (#1194)
* Update rust_api.yml

* Update rust_api.yml

* Update rust_api.yml

* Update rust_api.yml
2022-10-14 14:35:49 +08:00
Li Zhang 8c164ab3e5
[Fix] Detect filesystem library in CMake (#1190)
* detect filesystem library in CMake

* add filesystem.cmake
2022-10-14 12:52:16 +08:00
hanrui1sensetime c35099ef0c
fix layer norm when torch>=1.12 (#1168) 2022-10-11 14:29:13 +08:00
Li Zhang f389a68dd4
[Enhancement] Add a device field for `mmdeploy_mat_t` (#1176)
* add device field for mmdeploy_mat_t

* fix lint
2022-10-11 13:58:49 +08:00
Qingren fd21b98efa
[Docs] add the support information about MMPose Hourglass (#1118)
* [Docs] add the support information about MMPose Hourglass

* * add Hourglass support config

* update benchmark doc

* modify Hourglass AP under pytorch backend

* add regression test for Hourglass

* *update 03-benchmark/benchmark.md

* * modify mmpose.yml to ignore ncnn int8 test

* add trt_fp16 test results

* * add openvino test result

* * modify supported_models.md
2022-10-10 16:38:54 +08:00
RunningLeon 41fcc2242f
log cmd info for regresstion test (#1146)
* add log to regresstion test

* update for win

* update mmseg reg yml
2022-10-10 16:23:24 +08:00
AllentDan 76b837194f
Update timer (#1158)
* update time counter

* update test.py

* fix ci
2022-10-10 16:22:19 +08:00
Mengyang Liu ee1b4d756d
Update rust_api.yml (#1172) 2022-10-10 15:59:34 +08:00
tpoisonooo 5cdf29339b
feat(tools/scripts): add auto install jetson orin (#1105)
* feat(tools/scripts): add auto install jetson orin

* docs(script): rename file

* fix(script): if clause error

* style(scripts): typo
2022-10-09 15:53:19 +08:00
达芬奇 895d0749ef
Supplemental a parameter "device" (#1165)
* Supplemental a parameter "device"
补充一个参数“device”

* 补充一个参数“device”
Supplemental a parameter "device"
2022-10-09 14:26:14 +08:00
Mengyang Liu b2cb5722f7
Update get_started.md (#1155) 2022-10-08 09:16:54 +08:00
lvhan028 917643fcac
bump version to 0.9.0 (#1115) 2022-09-29 19:48:52 +08:00
AllentDan d153b5aa0a
add rewrite for ort (#1138) 2022-09-29 18:35:51 +08:00
hanrui1sensetime 161f27d493
fix mmedit test picture (#1131) 2022-09-29 17:13:23 +08:00
AllentDan 23e84f46ff
update mmcls yaml (#1137) 2022-09-29 17:09:17 +08:00
q.yao d282503012
update detyaml (#1133) 2022-09-29 12:14:06 +08:00
lvhan028 613acb366c
fix prebuilt error (#1123) 2022-09-28 17:52:09 +08:00
lvhan028 290d0d6e74
reorg demo/csrc (#1119)
* reorg demo/csrc

* disable det_cls and det_pose build
2022-09-28 11:47:00 +08:00
lvhan028 1da5464e11
reformat supported backends table in readme (#1109)
* reformat supported device and platforms

* use capital CPU
2022-09-27 20:05:32 +08:00
Chen Xin 0720ed8404
fix tracer (#1107) 2022-09-27 15:24:57 +08:00
Mengyang Liu 7da5c1408e
feat(CI): add rust-mmdeploy (#1100)
* Add CI of rust api

* Bug fixed

* Install Rust with actions

* Fix bug

* Fix bug

* Fix bug

* Fix bug

* Fix bug

* Add debugger-action

* Add debugger-action

* Fix bug

* Readd debugger

* Update mmdeploy dir path

* Update mmdeploy dir path

* Fix ld error

Co-authored-by: Liu Mengyang <liumengyang@Lius-MacBook-Pro.local>
2022-09-27 15:07:39 +08:00
Mengyang Liu 0effa59440
Split demos of C and C++ SDK into two subdirectories (#1099)
* Split demos of C and C++ SDK into two subdirectories

* Split demos of C and C++ SDK into two subdirectories

* Split demos of C and C++ SDK into two subdirectories

* Split demos of C and C++ SDK into two subdirectories

* Combine add_example
2022-09-27 13:40:04 +08:00
tpoisonooo c5e4fcffbc
docs(quantization.md): remove ppq commit (#1095) 2022-09-27 12:35:24 +08:00
tpoisonooo 14e31fb85a
fix(regression_test): use cuda:0 as default (#1020)
* fix(regression_test): use cuda:0 as default

* fix(pillar_scatter.py): fix scaternd rewrite
2022-09-26 16:11:43 +08:00
Li Zhang bf887cc8bc
[Enhancement] Refactor SDK pipeline (#938)
* unify C API naming

* fix demo and move apis/c/* -> apis/c/mmdeploy/*

* fix lint

* WIP refactor pipeline

* backward compatibility

* working pipeline demo

* add text det-recog demo

* add det-pose demo

* fix build

* fix demo

* add environment interface

* add environment to pass scheduler & model info at runtime

* update demos

* add pipeline API for Python

* fix `FromPyObject`

* fix for opencv-4.2

* environment -> context, improve pipeline

* python model interface

* fix cmake

* fix python & cmake

* context & C++ pipeline API

* minor fix

* improve API

* fix shared libs

* refresh C/Python API

* propagate context

* fix  python demo

* fix

* add namespace

* fix namespace

* fix mis-changed strings

* fix

* fix python api

* rename

* clean-up

* fix pose detector

* clean-up

* clean-up

* clean-up

* fix python API build

* fix CI

* fix lint

* fix lint

* fix lint & demo

* install pipeline.hpp

* fix MSVC shared library build

* fix sample

* fix MSVC monolithic build

* minor fix
2022-09-26 16:11:14 +08:00
q.yao 6ac9c4d7a8
[Fix] fix det with static shape (#1049)
* fix det with static shape

* update rotated detection

* fix resize keep ratio
2022-09-23 14:45:57 +08:00
tpoisonooo 676f1bf49c
improvement(ubuntu_utils.py): check upstream libopencv-dev version (#1068) 2022-09-23 10:21:09 +08:00
tpoisonooo 107ae8499d
docs(jetsons.md): fix desc (#1090)
* docs(jetsons.md): fix desc

* docs(jetsons.md): update
2022-09-23 10:14:00 +08:00
q.yao ea7706cbfd
fix layer norm (#1015) 2022-09-21 16:24:47 +08:00
BrokenArrow fbe7586415
Add result of quantization of TextSnake (#1074)
* 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
2022-09-21 15:28:28 +08:00
AllentDan e3859004ba
add mod rewriter for TRT (#1024) 2022-09-21 14:47:36 +08:00
whooray 1c5dcb799b
[Fix] fix broken link in docs english version write_config.md (#1078)
* fix typo error for how to write model config link

* Update write_config.md

zh_cn version does not exist
2022-09-20 17:51:19 +08:00
q.yao 6f5161b2fa
fix mmrotate int8 (#1050) 2022-09-19 17:10:40 +08:00
Chen Xin 7002ad21c2
fix ort-gpu inference (#1053) 2022-09-19 17:08:29 +08:00
Qingren fd07b26c2e
[Feature] Add mmpose configs for compatibility with Hourglass model in ncnn backend (#1064)
* [FEATURE] add mmpose configs for compatibility with Hourglass model

[Motivation]
- The added configs are aim to support Hourglass pose-detection model in ncnn backend.
- Hourglass model needs explicit input shape with 256x256 or 384x384.
- Hourglass model can be quantitized to int8 successfully in ncnn backend.

[Complementary]
The mmpose config of Hourglass mode is in:
- https://github.com/open-mmlab/mmpose/blob/master/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hourglass52_coco_256x256.py
- https://github.com/open-mmlab/mmpose/blob/master/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hourglass52_coco_384x384.py
Quantitization results are shown in https://github.com/Qingrenn/mmdeploy-summer-camp/blob/main/week4/result.md

* Keep only one config (pose-detection_ncnn-int8_static-256x256.py) and remove the others.
2022-09-19 14:13:55 +08:00
Qingren 18ccb15b7b
[Feature] Add Hourglass pose detection quantization evaluation result. (#1066)
Detail results: https://github.com/Qingrenn/mmdeploy-summer-camp/blob/main/week4/result.md
2022-09-19 14:09:46 +08:00