Commit Graph

813 Commits (a3311b0bbb6a18bef1a55f7d2e36dcc94a2a5e09)
 

Author SHA1 Message Date
AllentDan a3311b0bbb
enable TRT parse ONNX model from file (#1735) 2023-02-09 15:54:37 +08:00
Li Zhang f5a05b5219
[Refactor] Support batch inference with shape clustering (#1668)
* refactor `NetModule`

* name

* fix sorting

* fix indices
2023-02-08 20:14:28 +08:00
q.yao d8e4a78636
[Improvement] Better unit test. (#1619)
* update test for mmcls and mmdet

* update det3d mmedit mmocr mmpose mmrotate

* update mmseg

* bug fixing

* refactor ops

* rename variable

* remove comment
2023-02-08 11:30:59 +08:00
Li Zhang 5de0ecfcaf
[Fix] Add an option to flip webcam inputs for pose tracker demo (#1725) 2023-02-07 20:27:43 +08:00
Li Zhang 2b18596795
[Enhancement] Optimize C++ demos (#1715)
* optimize demos

* show text in image

* optimize demos

* fix minor

* fix minor

* fix minor

* install utils & fix demo file extensions

* rename

* parse empty flags

* antialias

* handle video complications
2023-02-07 19:08:46 +08:00
RunningLeon 31f422244b
fix stale workflow (#1713)
* fix stale workflow

* Update stale.yml
2023-02-06 21:17:26 +08:00
AllentDan 12b3d18c7a
[Fix] fix torch allocator resouce releasing (#1708)
* delete root logger and add condition before calling caching_allocator_delete

* fix lint error

* use torch._C._cuda_cudaCachingAllocator_raw_delete
2023-02-06 11:35:44 +08:00
Chen Xin b85f34141b
[Feature] Support feature map output for mmsegmentation (#1625)
* add feature map output for mmseg

* update api

* update demo

* fix return

* update format_shape

* fix lint

* update csharp demo

* update python demo && api

* fix coreml build

* fix lint

* better sort

* update

* update cpp demo & add missing header

* change to CHW

* update csharp api

* update isort version to 5.12.0

* fix python api

* fix log

* more detail api docs

* isort support python3.7

* remove isort change

* remove whitespace

* axes check

* remove FormatShapeImpl

* minor

* add permute tc

* remove stride buffer
2023-02-03 20:47:55 +08:00
AllentDan 7d085bee0e
directly set pytorch metric when it's empty for regression_test.py (#1704) 2023-02-03 11:25:11 +08:00
KerwinKai 23eed5c265
[Bug] Fixed ncnn model conversion errors in Dockerfile(no module name 'ncnn. ncnn',) (#1696)
* Update Dockerfile

* Update Dockerfile

* Update Dockerfile
2023-02-03 10:22:25 +08:00
q.yao 5fdf00324b
[Fix] add bounds to avoid large resource usage of nms operator on jetson (#1686)
* fix trt nms jetson

* update-for-comment

* clang format
2023-02-01 14:11:43 +08:00
q.yao 99d6fb3190
fix ascend (#1667) 2023-01-31 16:49:41 +08:00
tripleMu 85320df2b4
Fix isort lint error by upgrading it to 5.11.5 (#1685) 2023-01-31 13:31:59 +08:00
lvhan028 b101a4af65
[Enhancement] remove MMDEPLOY_BUILD_SDK_CXX_API option (#1688)
* remove MMDEPLOY_BUILD_SDK_CXX_API option

* update

* update
2023-01-31 13:29:59 +08:00
Li Zhang 3d425bbb9f
[Feature] Pose tracker C/C++/Python API&demos (#1663)
* add PoseTracker API

* add mahalanobis distance, add det_pose demo

* simplify api

* simplify api

* fix cmake & fix `CropResizePad`

* ignore out of frame bboxes

* clean-up

* fix lint

* add c api docs

* add c++ api docs/comments

* fix gcc7 build

* fix gcc7+opencv3

* fix stupid lint

* fix ci

* add help info & webcam support for C++ pose tracker demo

* add webcam support for Python pose tracker demo

* fix lint

* minor

* minor

* fix MSVC build

* fix python binding

* simplify module adapter

* fix module adapter

* minor fix
2023-01-31 11:24:24 +08:00
AllentDan 093badf90c
fix rknn output index error in SDK (#1683) 2023-01-30 20:50:06 +08:00
q.yao 8a050f10dc
suppress onnx optimizer warning (#1593) 2023-01-20 00:25:50 +08:00
tpoisonooo 7e48fb2905
improvement(tools/scripts): pip install with user environment (#1660) 2023-01-20 00:19:37 +08:00
Li Zhang 8bb3fcc6d8
fix 'cvtcolor' error in the preprocessing of single channel images (#1666) 2023-01-20 00:04:42 +08:00
q.yao 513b1c3cfb
Fix coreml (#1658)
* fix coreml topk

* update

* fix lint
2023-01-19 11:42:18 +08:00
kaizhong bce276ef24
[Feature]: add a tool to generate supported-backends markdown table (#1374)
* convert2markdown

* update yaml2mardown code

* code update

* add parse_args

* add parse_args

* add parse_args

* add parse_args

* add website list

* add website list

* add website list

* add website list

* add website list

* add website list

* add website list

* add url in yaml

* add table in convert

* add table in convert

* From yaml export markdown

* From yaml export markdown

* From yaml export markdown

* From yaml export markdown

* From yaml export markdown

* From yaml export markdown

* Rename convert.py to generate_md_table.py

generate_markdownd_table

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* docs(project): sync en and zh docs

* Update mmaction.yml

* add backends parser

* add backends parser

* Add type for the codeblock.

* move to useful tools
2023-01-18 16:32:26 +08:00
tpoisonooo 968b4b0b60
fix(requirements): codebase version (#1643) 2023-01-13 16:09:37 +08:00
Chen Xin c458e2a524
[Enhancement] Speedup TopDownAffine by CropResizePad (#1486)
* "use 'CropResizePad' to speed up topdownaffine"

* add missing header
2023-01-13 16:08:29 +08:00
hanrui1sensetime 9d3b494079
[Fix] Fix visualize api bug (#1641)
* fix visualize api bug

* fix visualize
2023-01-13 10:42:57 +08:00
Chen Xin 9a1f4e6145
[Fix] Fix example standalone build for msvc (#1626)
* fix example build for msvc

* move /Zc:__cplusplus to core
2023-01-11 10:55:17 +08:00
RunningLeon 3527412127
change log file extension to 'txt' in regression test(#1608) 2023-01-10 17:42:55 +08:00
Nghia 1b048d88ca
fixed script errors when calling miniconda.sh (#1599) 2023-01-10 13:52:24 +08:00
q.yao 0737a59f44
[Improvement] Support auto release note (#1589)
* Support auto release note

* update labels
2023-01-10 10:54:25 +08:00
hanrui1sensetime d5bd0072a2
fix android build command (#1620) 2023-01-10 10:44:49 +08:00
Li Zhang e4ad0d4c45
[Fix] Fix aligned allocations on Android (#1612)
* fix android alignment

* fix typo

* fix size
2023-01-06 18:04:28 +08:00
Li Zhang 4463572311
Fix debug build for PoseTracker (#1601) 2023-01-03 14:24:11 +08:00
Chen Xin c0ca074c11
Fix build error on windows-cuda platform (#1598) 2023-01-03 12:12:20 +08:00
lvhan028 c3986cebe8
bump version to v0.12.0 (#1594) 2022-12-30 16:17:37 +08:00
hanrui1sensetime 20b2aff660
[Fix] Fix batch inference error for Mask R-CNN (#1575)
* fix Mask R-CNN for multi-batch

* fix flake8

* fix bug

* use Sequence instead list

* fix docstring

* only test_img accept list input
2022-12-30 14:26:33 +08:00
Li Zhang 20e0563682
[Enhancement] Optimize pose tracker (#1460)
* sync master

* suppress overlapped tracks

* add CUDA WarpAffine

* export symbols

* fix linkage

* update pose tracker

* clean-up

* fix MSVC build

* fix MSVC build

* add ffmpeg cli command
2022-12-29 19:12:55 +08:00
tpoisonooo f62352a5fa
fix(README): badge error and add github action status (#1548)
* fix(README): badge error and add github action status

* docs(REAMDE): fix badge

* docs(README): update color

* docs(REAMEDE): update color

* docs(README): update table
2022-12-29 16:08:29 +08:00
hanrui1sensetime f21dc4e7d3
Cherry-pick #1352 to fix ops unittest seg-fault error (#1556)
* cherry-pick PR1352 to master

* fix test_ops with teardown and skip

* remove useless line

* fix lint

Co-authored-by: q.yao <yaoqian@sensetime.com>
2022-12-29 12:08:40 +08:00
q.yao fc98472e9c
[Refactor] update tutorial about how to support new backend (#1574) 2022-12-29 12:05:31 +08:00
Li Zhang e3f033ee5d
build monolithic SDK by default (#1577) 2022-12-28 11:44:20 +08:00
AllentDan 85b7b967ee
[Feature] Support probability output for segmentation (#1379)
* add do_argmax flag

* sdk support

* update doc

* replace do_argmax with with_argmax

* add todo
2022-12-26 15:48:07 +08:00
q.yao d113a5f1c7
[Refactor] refactor is_available, check_env (#1540)
* refactor is available

* remove try catch in apis

* fix trt check env

* fix ops_info

* update default value

* remove backend list

* optimial pycuda

* update requirement, check env for rknn
2022-12-23 12:06:32 +08:00
q.yao 5285caf30a
[Refactor] Add 'to_backend' in BackendManager (#1522)
* Refactor to backend

* export_postprocess_mask = False as defailt

* update zh_cn docs

* solve comment

* fix comment
2022-12-21 14:04:16 +08:00
AllentDan 26d71ce0a8
add 'is_batched' argument to pipeline.json (#1560) 2022-12-21 10:45:00 +08:00
BuxianChen f9f351ae1f
update FAQ about copying onnxruntime dll to 'mmdeploy/lib' (#1554) 2022-12-20 14:39:31 +08:00
Michał Antoszkiewicz 202bf00eb7
Fix 'cannot seek vector iterator' in debug windows build (#1555)
Signed-off-by: Michal Antoszkiewicz <mantoszkiewicz@codeflyers.com>

Signed-off-by: Michal Antoszkiewicz <mantoszkiewicz@codeflyers.com>
2022-12-20 10:13:33 +08:00
Chen Xin dbc4b26dc1
fix cuda10.2 build (#1539) 2022-12-16 10:15:15 +08:00
tpoisonooo 77c2ee5feb
fix(tools/scripts): build aarch option (#1530) 2022-12-15 20:41:59 +08:00
Chen Xin c72f2eaa31
[Docs] Add mmaction2 sphinx-doc link (#1541)
* add mmaction2 sphinx doc

* consistent with other doc formats

* change title

* fix ci

* add missing coreml sphinx doc
2022-12-15 19:01:34 +08:00
GY 05ed8e16ea
update to ppl.nn v0.9.1 and ppl.cv v0.7.1 (#1356) 2022-12-13 14:21:24 +08:00
q.yao 7cb4b9b18a
[Enhancement] Support tvm (#1216)
* finish framework

* add autotvm and auto-scheduler tuner

* add python deploy api

* add SDK net(WIP

* add sdk support

* support det, support vm

* fix vm sdk

* support two stage detector

* add instance seg support

* add docstring

* update docs and ut

* add quantize

* update doc

* update docs

* synchronize stream

* support dlpack

* remove submodule

* fix stride

* add alignment

* support dlpack

* remove submodule

* replace exclusive_scan

* add backend check

* add build script

* fix comment

* add ci

* fix ci

* ci fix2

* update build script

* update ci

* add pytest

* update sed command

* update sed again

* add xgboost

* remove tvm ut

* update ansor runner

* add stream sync

* fix topk

* sync default stream

* fix tvm net

* fix window
2022-12-12 21:19:40 +08:00