676f1bf49c
improvement(ubuntu_utils.py): check upstream libopencv-dev version ( #1068 )
2022-09-23 10:21:09 +08:00
107ae8499d
docs(jetsons.md): fix desc ( #1090 )
...
* docs(jetsons.md): fix desc
* docs(jetsons.md): update
2022-09-23 10:14:00 +08:00
ea7706cbfd
fix layer norm ( #1015 )
2022-09-21 16:24:47 +08:00
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
e3859004ba
add mod rewriter for TRT ( #1024 )
2022-09-21 14:47:36 +08:00
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
6f5161b2fa
fix mmrotate int8 ( #1050 )
2022-09-19 17:10:40 +08:00
7002ad21c2
fix ort-gpu inference ( #1053 )
2022-09-19 17:08:29 +08:00
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
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
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
50bd6b1703
improvement(visualize.py): headless enable inference ( #1041 )
...
* improvement(visualize.py): split render and display
* fix(visualize.py): skip render and save for headless device
* docs(deploy.py): update desc
2022-09-19 11:30:47 +08:00
cbe767efb1
[Fix] Fix docs under supported-backends fold ( #1061 )
...
* fix docs of supported-backends
* fix docs
2022-09-18 13:36:28 +08:00
a1a19f0fc1
Fixed typo for install commands for TensorRT runtime ( #1025 )
...
* Fixed typo for install commands for TensorRT runtime
* Apply typo-fix on 'cn' documentation
Co-authored-by: Tümer Tosik <tumer_t@hotmail.de>
2022-09-15 20:23:07 +08:00
2f47262d7a
Fix `RoIAlignFunction` error for CoreML backend ( #1029 )
2022-09-14 17:50:37 +08:00
538c9cfbb1
docs(scripts): update auto install desc ( #1036 )
2022-09-14 17:49:29 +08:00
441d0e2703
fix two stage batch dynamic ( #1046 )
2022-09-14 17:48:34 +08:00
615668ec63
update api in doc ( #1021 )
2022-09-14 17:47:26 +08:00
e912e86d24
BUG P0 ( #1044 )
2022-09-14 17:20:11 +08:00
b87afb9ebb
fix mmdeploy builder on windows ( #1018 )
...
* fix mmdeploy builder on windows
* add pyyaml
* fix lint
2022-09-09 15:03:55 +08:00
f2bc808fe3
New issue template ( #1007 )
...
* update bug report
* update issue template
* update bug-report
2022-09-07 16:00:37 +08:00
8e9578c04d
fix(CI): update link checker ( #1008 )
2022-09-07 15:59:48 +08:00
b310ba8d3e
bump version to v0.8.0 ( #1009 )
2022-09-07 10:53:50 +08:00
b602356181
[Fix] Add isolated option for TorchScript SDK backend ( #1002 )
...
* add option for TorchScript SDK backend
* add doc
* format
2022-09-06 12:24:07 +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
a0fb3be0df
support coreml ( #760 )
...
* sdk inference
* fix typo
* fix typo
* add convert things
* fix missling name
* add cls support
* add more pytorch rewriter
* add det support
* support det wip
* make Model export model_path
* fix nms
* add output back
* add docstring
* fix lint
* add coreml build action
* add zh docs
* add coreml backend check
* update ci
* update
* update
* update
* update
* update
* fix lint
* update configs
* add return value when error occured
* update docs
* update docs
* update docs
* fix lint
* udpate docs
* udpate docs
* update
Co-authored-by: grimoire <streetyao@live.com>
2022-09-05 19:55:47 +08:00
3d092bfb39
fix mmdet showresult ( #999 )
...
* fix mmdet showresult
* Consider compatibility
* mmdet showresult add *args
* Revert "mmdet showresult add *args"
This reverts commit 82265a31cf
2022-09-05 18:27:02 +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
e21cad84e0
fix(backend): disable cublaslt for cu102 ( #947 )
...
* fix(backend): disable cublaslt for cu102
* fix
* fix(backend): update
* fix(tensorrt/util.py): add find cuda version
* fix
* fix(CI): first use cmd to get cuda version
* docs(tensorrt/utils.py): update docstring
2022-09-05 14:52:43 +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
9918d29212
add missing sqrt for PAAHead's score calculation ( #984 )
...
Co-authored-by: xianghongyi1 <xianghongyi1@sensetime.com>
2022-09-02 18:25:50 +08:00
9b3db48de9
fix(CI): ort test all pipeline ( #985 )
2022-09-02 17:34:22 +08:00
306616fc34
fix(CI): typo ( #983 )
2022-09-02 16:06:53 +08:00
cbedf1cc30
fix regression test ( #958 )
...
* fix reg
* set sdk wrapper device id
* resolve comment
2022-09-02 11:28:12 +08:00
5874f1039b
Add CI to test full pipeline ( #966 )
...
* add mmcls full pipeline test ci
* update
* update
* add mmcv
* install torch
* install mmdeploy
* change clone with https
* install mmcls
* update
* change mmcls version
* add mmcv version
* update mmcls version
* test sdk
* tast with imagnet
* sed pipeline
* print env
* update
* move to backend-ort ci
* install mim
2022-09-02 10:55:53 +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
a6ed7eddc5
fix mmroate ( #976 )
2022-09-02 10:45:49 +08:00
38bcc43256
CI(tools/scripts): add submodule init and update ( #977 )
2022-09-02 10:28:11 +08:00
8a40f195bc
remove Release dir in mmdeploy package ( #960 )
2022-08-31 15:48:42 +08:00
ac9db5b4e7
[Fix] Close onnx optimizer for ncnn ( #961 )
...
* close onnx optimizer for ncnn
* fix docformatter
* fix lint
2022-08-31 15:48:08 +08:00
eed69b14e2
fix ci ( #964 )
2022-08-31 14:36:15 +08:00
638e33a964
add_multi_label_postprocess ( #950 )
...
* 'add_multi_label_postprocess'
* fix pre-commit
* delete partial_sort
* delete idx
* delete num_classes and num_classes_
* Fix right brackets and spelling errors in lines 19 and 20
Co-authored-by: gaoying <gaoying@xiaobaishiji.com>
2022-08-30 19:02:42 +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
f7e0905e95
docs(convert_model): update description ( #956 )
2022-08-30 10:37:07 +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
tpoisonooo
q.yao
BrokenArrow
AllentDan
whooray
Chen Xin
Qingren
Jingwei Zhang
ichitaka
Jelle Maas
q.yao
lvhan028
Li Zhang
RunningLeon
munhou
Hongyi Xiang
hanrui1sensetime
gy77