140e0519e6
[Fix] Export `mmdeploy` only in monolithic build ( #1798 )
...
* export only `mmdeploy` in monolithic build
* export dynamic backends
2023-03-21 11:21:19 +08:00
06dac732c9
optimize mmpose postprocess ( #1887 )
2023-03-21 11:06:18 +08:00
34c68663b6
[Sync] Sync Java API to master ( #1856 )
...
* sync rotated detector java api to master
* sync mmseg score output to master
* sync java docs for demo
* sync java docs for master
2023-03-13 11:31:39 +08:00
48291f01c8
docs(project): highlight version ( #1871 )
2023-03-13 10:23:52 +08:00
12a130262f
add unified device guard ( #1855 )
2023-03-10 19:16:13 +08:00
bcb93ead58
[Enhancement] Add optional `softmax` in `LinearClsHead` ( #1858 )
...
* add softmax in cls postprocess
* minor
2023-03-09 16:54:15 +08:00
f69c636a2e
mmocr FPNC neck support asf module ( #1828 )
...
* mmocr FPNC neck support asf module
* mmocr FPNC neck support asf module
---------
Co-authored-by: lishengxi <mtdp@MacBook-Pro-8.local>
2023-03-03 15:27:02 +08:00
cb964f6a58
[Fix] Fix Debian aarch64 cross compiling ( #1806 )
...
* fix debian cross compiling
* comment
* minor
2023-03-03 12:41:52 +08:00
d95950d705
[Feature] Dynamically load net module to remove dependencies of mmdeploy.so ( #1776 ) ( #1822 )
...
* dynamic load net module
* export xxx_net
* add runpath
* link dl
* remove -ldl for macos
* fix rpath
* module -> shared
* set MMDEPLOY_DYNAMIC_BACKEND OFF when MMDEPLOY_BUILD_SDK_MONOLITHIC is OFF
2023-03-03 11:48:59 +08:00
7de413a19c
[Feature] Sync csharp apis with newly added c apis && demo ( #1718 )
...
* sync c api to c#
* fix typo
* add pose tracker c# demo
* udpate gitignore
* remove print
* fix lint
* update rotated detection api
* update rotated detection demo
* rename pose_tracking -> pose_tracker
* use input size as default
2023-03-02 09:20:41 +08:00
7fed511f09
disable building demos when preparing prebuilt package ( #1810 )
2023-02-28 21:16:35 +08:00
7029e90064
avoid linking static libs in monolithic build ( #1797 )
2023-02-23 14:21:51 +08:00
f78a452681
fix missing include for gcc-10 build ( #1802 )
2023-02-23 12:05:25 +08:00
eb75bee921
add `Model::ReadConfig` & simplify handle creation ( #1738 )
2023-02-21 17:09:07 +08:00
c941045156
fix normalization to_rgb option ( #1771 )
2023-02-21 17:08:34 +08:00
4bb8920b61
Fix trtlogger instead of mm logger ( #1755 )
...
* Fix trtlogger instead of mm logger
* Reset trt logger to mmdeploy logger
* rename logger name
2023-02-20 16:45:47 +08:00
fd47fa2071
[Enhance] support TensorRT engine for onnxruntime ( #1739 )
...
* Support trt engine for onnxruntime
* Apply lint
* Check trt execution provider
* Fix typo
* Fix provider order
* Check device
2023-02-20 14:18:09 +08:00
b1be9c67f3
[Fix] Fix palette generation on opencv-3.x ( #1778 )
2023-02-17 18:33:38 +08:00
02d5a09989
bump version to 0.13.0 ( #1753 )
2023-02-16 14:15:19 +08:00
fa9aaa9d61
[Enhancement] Loosen protobuf version criteria for onnx upgrade ( #1759 )
...
- onnx<1.13.0 has high security issue
(https://github.com/advisories/GHSA-ffxj-547x-5j7c )
- Python packages depending on mmdeploy cannot upgrade onnx as
- onnx==1.13.0 depends on protobuf>=3.20.2
- mmdeploy depends on protobuf<=3.20.1
- Suggesting [protobuf<=3.20.2] for quick solution
Signed-off-by: Songki Choi <songki.choi@intel.com>
2023-02-15 16:03:15 +08:00
599c701655
[Enhancement] Support cmake configure when system exists multiple cuda versions. ( #1740 )
...
* update cmake
* typos
2023-02-14 16:20:47 +08:00
e519898adb
Fix bug in remove_imports ( #1743 )
...
* Fix bug in remove_imports
IndexError: list index out of range error as `model.opset_import list` is changing dynamically
* pre-commit fix
2023-02-13 19:46:24 +08:00
cadc2658f3
Fix `WarpBbox` and memory leak in `TextRecognizer` ( #1745 )
2023-02-13 19:43:25 +08:00
0f5b149557
fix instance norm double free ( #1748 )
2023-02-13 19:42:37 +08:00
31b099a37b
add coco whole-body skeleton ( #1736 )
2023-02-09 18:31:35 +08:00
a3311b0bbb
enable TRT parse ONNX model from file ( #1735 )
2023-02-09 15:54:37 +08:00
f5a05b5219
[Refactor] Support batch inference with shape clustering ( #1668 )
...
* refactor `NetModule`
* name
* fix sorting
* fix indices
2023-02-08 20:14:28 +08:00
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
5de0ecfcaf
[Fix] Add an option to flip webcam inputs for pose tracker demo ( #1725 )
2023-02-07 20:27:43 +08:00
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
31f422244b
fix stale workflow ( #1713 )
...
* fix stale workflow
* Update stale.yml
2023-02-06 21:17:26 +08:00
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
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
7d085bee0e
directly set pytorch metric when it's empty for regression_test.py ( #1704 )
2023-02-03 11:25:11 +08:00
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
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
99d6fb3190
fix ascend ( #1667 )
2023-01-31 16:49:41 +08:00
85320df2b4
Fix isort lint error by upgrading it to 5.11.5 ( #1685 )
2023-01-31 13:31:59 +08:00
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
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
093badf90c
fix rknn output index error in SDK ( #1683 )
2023-01-30 20:50:06 +08:00
8a050f10dc
suppress onnx optimizer warning ( #1593 )
2023-01-20 00:25:50 +08:00
7e48fb2905
improvement(tools/scripts): pip install with user environment ( #1660 )
2023-01-20 00:19:37 +08:00
8bb3fcc6d8
fix 'cvtcolor' error in the preprocessing of single channel images ( #1666 )
2023-01-20 00:04:42 +08:00
513b1c3cfb
Fix coreml ( #1658 )
...
* fix coreml topk
* update
* fix lint
2023-01-19 11:42:18 +08:00
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
968b4b0b60
fix(requirements): codebase version ( #1643 )
2023-01-13 16:09:37 +08:00
c458e2a524
[Enhancement] Speedup TopDownAffine by CropResizePad ( #1486 )
...
* "use 'CropResizePad' to speed up topdownaffine"
* add missing header
2023-01-13 16:08:29 +08:00
9d3b494079
[Fix] Fix visualize api bug ( #1641 )
...
* fix visualize api bug
* fix visualize
2023-01-13 10:42:57 +08:00
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
Li Zhang
Chen Xin
hanrui1sensetime
tpoisonooo
Shengxi Li
lvhan028
SineYuan
tripleMu
YH
q.yao
Songki Choi
Chen Xin
Eugene Liu
AllentDan
RunningLeon
KerwinKai
kaizhong