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
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
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
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
af4d304004
support torchjit mdcn ( #1508 )
2022-12-12 10:28:49 +08:00
8ea3dc943f
[Fix] Fix for torch113 for master ( #1488 )
2022-12-08 17:17:27 +08:00
4046e13146
Reformat multi-line logs and docstrings ( #1489 )
2022-12-06 19:50:58 +08:00
2c9861555f
[Enhancement] add mmaction.yml for test ( #1455 )
...
* add mmaction.yml for test
* t# This is a combination of 2 commits.
add missing file
* fix typo
* remove
2022-11-29 18:48:29 +08:00
047ab67c78
[Fix] fix visualization for partition ( #1424 )
...
* init
* lint
* pass output_names outside
* docstring & type hint
2022-11-29 11:40:00 +08:00
d9d3ded8bc
concat datasets pytorch metric ( #1447 )
2022-11-28 17:34:02 +08:00
d77aeaa480
[Refactor] Decouple preprocess operation and transformation ( #1353 )
...
* refactor SDK registry
* fix lint
* decouple transform logic and operations
* data management
* improve data management
* improve data management
* context management
* fix ResizeOCR
* fix operation fallback logic
* fix MSVC build
* clean-up
* sync master
* fix lint
* Normalize - add `to_float`, merge `cvtcolor` operations
* fix macOS build
* rename
* cleanup
* fix lint
* fix macOS build
* fix MSVC build
* support elena
* fix
* fix
* optimize normalize
* fix
* fix MSVC build
* simplify
* profiler
* use `throw_exception`
* misc
* fix typo
2022-11-28 14:46:05 +08:00
10e5cf6e0f
update reg test ( #1440 )
...
* give model path if stead of 'x' when conversion failed
* set --models with default value ['all']
* fix mmseg yml
2022-11-25 21:16:22 +08:00
9bbe3c0355
[Feat] Add end2end pointpillars & centerpoint(pillar) deployment for mmdet3d ( #1178 )
...
* add end2end pointpillars & centerpoint(pillar)
* fix centerpoint UT
* uncomment pycuda
* add nvidia copyright and remove post_process for voxel_detection_model
* keep comments
* add anchor3d_head init
* remove pycuda comment
* add pcd test sample
2022-11-24 16:14:50 +08:00
de96f51231
Update regresssion test to parse eval result from json ( #1310 )
...
* export metrics results to json
* fix mmedit
* update docs
* fix test failure
* fix
* fix mmocr metrics
* remove srgan config with no set5 test
2022-11-22 20:47:22 +08:00
99040d5655
[Refactor] better SDK registry ( #1368 )
...
* refactor SDK registry
* fix lint
* fix typo
* sync
* use nested namespace
* rename
2022-11-15 21:06:13 +08:00
d8e6229dc5
Support mmaction master ( #1183 )
...
* cpu format shape
* convert model
* python api
* speedup dataloader
* minor
* add cpp demo
* add visualize
* fix resize param order
* export pipeline.json
* fix three crop
* read SampleFrames from model_cfg
* minor
* lint
* move to a func
* speed up format shape cpu
* use input mat device
* fix comments
* fix comments
* update docs/benchmark
* docs/supported-codebases
* update tests/data
* fix lint
* fix lint
2022-11-04 14:15:36 +08:00
c4d428fd7d
Add model conversion support to rv1126 ( #1203 )
...
* WIP
* fix interpolate
* support yolov3 and retinanet
* support seg
* support ssd
* supports both partition types for retinanet and ssd
* mean std doc
* update doc, add UT
* support FSAF
* rename configs
* update dump info
* update
* python package installation doc
* update doc
* update doc
* doc
2022-11-02 11:04:22 +08:00
502a5696c5
update ( #1272 )
2022-10-31 14:12:28 +08:00
197a7ad425
fix efficientnet from mmcls ( #1260 )
...
* fix efficientnet from mmcls
* update
2022-10-27 16:20:39 +08:00
f2be2abeb5
[Feature] Add `Cond` node and pose tracker demo ( #1186 )
...
* add Cond node
* WIP PoseTracker
* fix pose tracker
* minor fix
* simplify design
* add timing
* sync
* visualize
* remove file check
2022-10-27 14:52:04 +08:00
1323ffcb50
[Refactor] Ease rewriter import ( #1166 )
...
* Ease rewriter import
* remove import
* add sar_encoder
* recover mha
2022-10-25 10:45:03 +08:00
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
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
954e0d2ca1
update symbolic rewriter ( #1122 )
...
* update symbolic rewriter
* update ut
2022-10-18 11:21:54 +08:00
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
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
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
161f27d493
fix mmedit test picture ( #1131 )
2022-09-29 17:13:23 +08:00
23e84f46ff
update mmcls yaml ( #1137 )
2022-09-29 17:09:17 +08:00
d282503012
update detyaml ( #1133 )
2022-09-29 12:14:06 +08:00
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
ea7706cbfd
fix layer norm ( #1015 )
2022-09-21 16:24:47 +08:00
e3859004ba
add mod rewriter for TRT ( #1024 )
2022-09-21 14:47:36 +08:00
0caeaf238c
[CustomOps] TensorRT Gather Topk Ops ( #1033 )
...
* add gather topk
* add shape inference and document
* fix faster rcnn
* reshape topk
* fix
2022-09-19 13:48:26 +08:00
124635ec5f
Add RKNN support. ( #865 )
...
* save codes
* support resnet and yolov3
* support yolox
* fix lint
* add mmseg support and a doc
* add UT
* update supported model list
* fix ci
* refine docstring
* resolve comments
* remote output_tensor_type
* resolve comments
* update readme
2022-09-06 11:48:39 +08:00
6b01a2e649
[Feature] Add option to fuse transform. ( #741 )
...
* add collect_impl.cpp to cuda device
* add dummy compute node wich device elena
* add compiler & dynamic library loader
* add code to compile with gen code(elena)
* move folder
* fix lint
* add tracer module
* add license
* update type id
* add fuse kernel registry
* remove compilier & dynamic_library
* update fuse kernel interface
* Add elena-mmdeploy project in 3rd-party
* Fix README.md
* fix cmake file
* Support cuda device and clang format all file
* Add cudaStreamSynchronize for cudafree
* fix cudaStreamSynchronize
* rename to __tracer__
* remove unused code
* update kernel
* update extract elena script
* update gitignore
* fix ci
* Change the crop_size to crop_h and crop_w in arglist
* update Tracer
* remove cond
* avoid allocate memory
* add build.sh for elena
* remove code
* update test
* Support bilinear resize with float input
* Rename elena-mmdeploy to delete
* Introduce public submodule
* use get_ref
* update elena
* update tools
* update tools
* update fuse transform docs
* add fuse transform doc link to get_started
* fix shape in crop
* remove fuse_transform_ == true check
* remove fuse_transform_ member
* remove elena_int.h
* doesn't dump transform_static.json
* update tracer
* update CVFusion to remove compile warning
* remove mmcv version > 1.5.1 dep
* fix tests
* update docs
* add elena use option
* remove submodule of CVFusion
* update doc
* use auto
* use throw_exception(eEntryNotFound);
* update
Co-authored-by: cx <cx@ubuntu20.04>
Co-authored-by: miraclezqc <969226879@qq.com>
2022-09-05 20:29:18 +08:00
ac3a12026d
fix mmdet ut ( #1001 )
2022-09-05 19:56:19 +08:00
9541be9c0b
TensorRT dot product attention ops ( #949 )
...
* add detr support
* fix softmax
* add placeholder
* add implement
* add docs and ut
* update testcase
* update docs
* update docs
2022-09-05 18:25:39 +08:00
792c27b054
[Feature] Ascend backend ( #747 )
...
* add acl backend
* support dynamic batch size and dynamic image size
* add preliminary ascend backend
* support dtypes other than float
* support dynamic_dims in SDK
* fix dynamic batch size
* better error handling
* remove debug info
* [WIP] dynamic shape support
* fix static shape
* fix dynamic batch size
* add retinanet support
* fix dynamic image size
* fix dynamic image size
* fix dynamic dims
* fix dynamic dims
* simplify config files
* fix yolox support
* fix negative index
* support faster rcnn
* add seg config
* update benchmark
* fix onnx2ascend dynamic shape
* update docstring and benchmark
* add unit test, update documents
* fix wrapper
* fix ut
* fix for vit
* error handling
* context handling & multi-device support
* build with stub libraries
* add ci
* fix lint
* fix lint
* update doc ref
* fix typo
* down with `target_link_directories`
* setup python
* makedir
* fix ci
* fix ci
* remove verbose logs
* fix UBs
* export Error
* fix lint
* update checkenv
Co-authored-by: grimoire <yaoqian@sensetime.com>
2022-09-05 12:08:36 +08:00
966d737a1b
Fix: skip tests for uninstalled codebases ( #987 )
...
* skip tests if codebase not installed
* skip ort run test
* fix mmseg
2022-09-03 15:07:08 +08:00
cbedf1cc30
fix regression test ( #958 )
...
* fix reg
* set sdk wrapper device id
* resolve comment
2022-09-02 11:28:12 +08:00
71e64786b7
Fix mmseg pointrend ( #903 )
...
* support mmseg:pointrend
* update docs
* update docs for torchscript
* resolve comments
2022-09-02 10:55:32 +08:00
eed69b14e2
fix ci ( #964 )
2022-08-31 14:36:15 +08:00
13920ec1a2
[Enhancement] Rewriter support pre-import function ( #899 )
...
* support preimport
* update rewriter
* fix batched nms ort
2022-08-30 12:32:43 +08:00
47d4e6f733
fix ut failed ( #951 )
2022-08-30 11:21:18 +08:00
f4decda86e
[Enhancement] Support DETR ( #924 )
...
* add detr support
* fix softmax
* add reg test, update document
2022-08-30 10:39:10 +08:00
18321eed51
[Bug] fix setitem with scalar or single element tensor ( #941 )
...
* fix setitem
* add copy symbolic
2022-08-29 18:56:17 +08:00
0111e1f10f
[Feature] add swin for cls ( #911 )
...
* add swin for cls
* add ut and doc
* reduce trt batch size
* add regression test
* resolve comments
* remove useless rewriting logic
2022-08-23 17:14:24 +08:00
cad0092801
[Fix] fix device error in dump-info ( #912 )
...
* fix device error in dump-info
* fix UT
2022-08-17 18:01:26 +08:00
670a504502
fix adaptive_avg_pool exporting to onnx ( #857 )
...
* fix adaptive_avg_pool exporting to onnx
* remove debug codes
* fix ci
* resolve comment
2022-08-12 09:38:46 +08:00
hanrui1sensetime
q.yao
q.yao
Chen Xin
AllentDan
Li Zhang
RunningLeon
Jiahao Sun
LiuYi-Up
SsTtOoNnEe
Qingren
Chen Xin