cfb9099077
fix ort wrap about input type ( #81 )
2022-01-19 19:12:29 +08:00
8ceb001d31
Support UNet in mmseg ( #77 )
...
* Repeatdataset in train has no CLASSES & PALETTE
* update result for unet
* update docstring for mmdet
* remove ppl for unet in docs
2022-01-19 19:11:04 +08:00
9aabae32aa
Added mask overlay to output image, changed fprintf info messages to … ( #55 )
...
* Added mask overlay to output image, changed fprintf info messages to stdout
* Improved box filtering (filter area/score), make sure roi coordinates stay within bounds
* clang-format
2022-01-19 14:56:37 +08:00
e6e32a9db4
[Feature] add yolox ncnn ( #29 )
...
* add yolox ncnn
* add ncnn android performance of yolox
* add ut
* fix lint
* fix None bugs for ncnn
* test codecov
* test codecov
* add device
* fix yapf
* remove if-else for img shape
* use channelshuffle optimize
* change benchmark after channelshuffle
* fix yapf
* fix yapf
* fuse continuous reshape
* fix static shape deploy
* fix code
* drop pad
* only static shape
* fix static
* fix docstring
2022-01-19 13:54:45 +08:00
997d111a6f
[Fix] Fixed device_id in tools/test.py for the CPU. ( #58 )
...
* [Fix] fix bugs for mmcls performance test (#269 )
* fix bugs for mmcls performance test
* fix yapf
* add comments of CLASSES attribute
* Rewrote the dictionary traversal for new versions of Python.
* Fix device_id for cpu
* Rewrite parse_device_id and tests
* Added None for cpu
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
2022-01-13 15:37:23 +08:00
bb655af629
Add Python wrapper for SDK ( #27 )
...
* add python API for detector
* integrate detection
* add python segmentor
* add segmentation support
* add classifier, text-detector, text-recognizer and restorer
* integrate classifier
* integrate textdet, textrecog and restorer
* simplify
* add inst-seg
* fix inst-seg
* integrate inst-seg
* Moidfy _build_wrapper
* better pipeline substitution
* use registry for backend model creation
* build Python module according to C API targets
* minor fix
* move sdk data pipeline to backend_config
* remove debugging lines
* add docstring for SDKEnd2EndModel
* fix type hint
* fix lint
* fix lint
* insert build/lib to sys.path
Co-authored-by: SingleZombie <singlezombie@163.com>
2022-01-13 11:31:51 +08:00
12ee956d36
[Enhancement]: Remove deepcopy in patch_model ( #61 )
...
* Remove deepcopy
* Fix test
2022-01-13 11:16:16 +08:00
6682cd0077
add OpenMMLab website and platform links ( #64 )
...
Co-authored-by: xiaomin <xiaomin@pjlab.org.cn>
2022-01-13 10:19:21 +08:00
76f96f09bc
remove partition configs and docs ( #59 )
2022-01-11 18:38:54 +08:00
fbce75e6bc
add comment and static decorator ( #60 )
2022-01-11 16:44:47 +08:00
d157243077
[Fix] move target_wrapper into utils ( #20 )
...
* move target_wrapper into utils
* fix for lint
* add typehint and docstring
* update unit test
* fix isort
* update import
2022-01-11 15:43:47 +08:00
d1528e5b34
Fix TensorRT 7 SSD ( #49 )
2022-01-11 11:10:10 +08:00
9fd15e3843
[Unittest] Add L2Norm unittest for default backend. ( #43 )
...
* add l2norm ut
* fix yapf
* fix test bugs
* fix yapf
* fix is_backend_output
2022-01-10 16:19:30 +08:00
81770e26c1
fix dynamic shape bug in mmseg ( #57 )
2022-01-10 15:47:13 +08:00
dbc12686ea
[Enhancement] use mmcv.utils.get_logger ( #24 )
...
* use mmcv.utils.get_logger
* add a unit test
* fix ut
* refine docstring
* fix lint
2022-01-10 15:46:42 +08:00
03e1213848
add gpu ci ( #35 )
...
* add gpu ci
* fix ci
* set mmcv==1.4.0 in ci config
* fix ci
* import nms in forward
* udpate
* change cuda ci
* change to cuda10.2
* change to torch1.9.0
* fix
* add cuda11.1
* add empty line
2022-01-10 11:14:17 +08:00
3e5c785d9a
[Fix] Support MMDet custom dataset ( #33 )
...
* Fix mmdet classes
* Fix classes in data_cfg
2022-01-10 10:40:47 +08:00
37a1b83567
dump cls_name ( #50 )
2022-01-07 15:03:01 +08:00
1a040036cc
[Fix] Avoid outputing empty tensor in NMS ( #42 )
...
* Remove slick op
* Fix tests
* Fix tests
* fix tests
2022-01-07 13:35:49 +08:00
de367b72bf
ncnn version 1208 ( #47 )
2022-01-07 11:04:28 +08:00
03ae26c91c
Refactor cuda resize ( #45 )
...
* refactor cuda resize
* add warning for ppl.cv < 0.6
* fix code style
2022-01-06 15:19:06 +08:00
b5d6c03628
Fix some type of error ( #18 )
...
* Fix some type
* Fix lint
* update
* update
* fix docstring
Co-authored-by: AllentDan <AllentDan@yeah.net>
2022-01-06 11:22:06 +08:00
3fd17ab6ff
[Refactoring]: Add get_dynamic_axes. ( #36 )
...
* [Fix] fix bugs for mmcls performance test (#269 )
* fix bugs for mmcls performance test
* fix yapf
* add comments of CLASSES attribute
* Fix input name
* support all codebases and update dump info
* fix docstring
* Added random names.
* onnx_config -> ir_config
* fix test
* fix test
* add a TODO
* use self.output_names
* Fixes
* Rewrite test_torch2onnx.
* Add get_dynamic_axes.
* Fix TestGetDynamicAxes
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
Co-authored-by: AllentDan <AllentDan@yeah.net>
Co-authored-by: grimoire <yaoqian@sensetime.com>
2022-01-06 11:21:48 +08:00
c6fccd0121
Fixed build using latest ppl.cv master ( #40 )
...
* Fixed build on latest ppl.cv master
* clang-format fix
2022-01-05 14:30:57 +08:00
f203306cf6
modified device selection ( #21 )
...
* modified device selection
device cannot sucessfully control through argments "device"
* update with_sync
* Update ORTWrapper
change the way to create ort session, previous work would load same model twice.
* Update wrapper.py
fixed for lint
* Update wrapper.py
* Update wrapper.py
remove the backslash
* formating
using yapf to format the file
Co-authored-by: AllentDan <AllentDan@yeah.net>
2021-12-31 18:26:51 +08:00
48bea16b31
【Docs】fix docs ( #32 )
...
* fix docs
* fix cn docs log link
* fix
* fix log link
2021-12-31 14:36:55 +08:00
ced3e06f5a
Update flake8 to GitHub in pre-commit ( #34 )
2021-12-31 13:00:23 +08:00
8cdb4abcc9
[Fix] Fix input names ( #12 )
...
* [Fix] fix bugs for mmcls performance test (#269 )
* fix bugs for mmcls performance test
* fix yapf
* add comments of CLASSES attribute
* Fix input name
* support all codebases and update dump info
* fix docstring
* Added random names.
* onnx_config -> ir_config
* fix test
* fix test
* add a TODO
* use self.output_names
* Fixes
* Rewrite test_torch2onnx.
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
Co-authored-by: AllentDan <AllentDan@yeah.net>
Co-authored-by: grimoire <yaoqian@sensetime.com>
2021-12-30 19:56:03 +08:00
6383da6db0
fix pplnn results for mmseg ( #31 )
2021-12-30 17:52:48 +08:00
db00e847c2
[Docs] add switch-language ( #25 )
...
* add switch-language
* Update shared menu
* Modify logo
* Modify image
* Modify image
* Modify css
* transparent logo
2021-12-30 12:36:01 +08:00
b55bf8ec1b
[Docs] update acknowledgement and MMDeploy's short introduction ( #15 )
...
* add mmdeploy short introduction
* add acknowledgement to OpenPPL team
* update acknowledgement
2021-12-29 19:24:03 +08:00
f693f7cc41
[Enhancement] support coverage ( #16 )
...
* support coverage
* test codecov action 2
2021-12-29 16:26:41 +08:00
f2594c624b
add openvino.md to index.rst ( #11 )
2021-12-27 20:21:08 +08:00
26d40fe883
fix ( #10 )
2021-12-27 13:45:35 +08:00
466ed64739
update links ( #9 )
...
* update links
* remove link
2021-12-27 13:01:27 +08:00
454d7fdc46
remove csrc/README.md ( #8 )
2021-12-27 11:35:25 +08:00
428ef05c07
[Other] Update readme tags ( #6 )
...
* correct url.
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
* Add readme tags
Co-authored-by: lvhan028 <lvhan_028@163.com>
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
2021-12-27 11:20:26 +08:00
3a8b9837ce
Url ( #7 )
...
* fix url Co-authored-by: maningsheng@sensetime.com
* fix url
Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com>
* fix url
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: del-zhenwu <56623710+del-zhenwu@users.noreply.github.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com>
Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: Semyon Bevzyuk <semen.bevzuk@gmail.com>
Co-authored-by: Zaida Zhou <58739961+zhouzaida@users.noreply.github.com>
Co-authored-by: del-zhenwu <56623710+del-zhenwu@users.noreply.github.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com>
2021-12-27 11:08:21 +08:00
cfd41d03e2
add ncnn latency benchmark to zh_cn ( #5 )
2021-12-27 10:20:15 +08:00
d8d3c354c3
correct url. ( #4 )
...
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
2021-12-24 22:16:23 +08:00
f4e152098b
update bug-report ( #1 )
...
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-24 21:39:14 +08:00
1a35cf85b4
fix intro ( #337 )
2021-12-24 18:49:09 +08:00
d79413fa32
update c-api's comments by following doxygen's guide ( #336 )
...
* update c-api's comments by following doxygen's guide
* fix according to review comments
2021-12-24 18:43:26 +08:00
09f14fa4b7
[Docs]Remove cn docs ( #335 )
...
* remove cn docs
* fix index.rst
* fix index.rst
2021-12-24 18:14:45 +08:00
15bdafed1f
[Docs]Add a support model list. ( #333 )
...
* add docs about support model
* fix docs
* fix support list
* fix docs
* fix format
* fix how to convert model
* fix en and cn docs about convert model
* fix bash
* fix docs format
* fix readme
* fix benchmark
* fix cn docs link
* rename support models
* rename
* fix docs
* fix cn benchmark
* fix benchmark
2021-12-24 17:20:06 +08:00
02e033ba5b
[Docs] Add zh_cn get_started ( #327 )
...
* start up
* zh-cn v0.1
* [Docs] Add a from-scratch example for "Get Started" (#326 )
* Add a from-scratch example
* Fix typo
* resolve comment
* bachslash
* Resolve comments
* Refine commands
* add cn docs
* Correct commands
* fixing...
* update zn-cn docs
* update en link
* add sdk's get-started (#331 )
* add sdk's get-started
* add SDK build command
* fix chinglish
* add sdk get start zh_cn
* update zh_cn cite
* fix command
* add selfsup/razor readme
* Fix command
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
2021-12-24 15:26:50 +08:00
8e19a08bcf
[Doc] Add other ncnn ops docs. ( #329 )
...
* add other ops
* fix comments
* add ncnn.md
* remove gpu
2021-12-24 14:27:03 +08:00
e355aad45f
[Docs] add ncnn latency benchmark ( #314 )
...
* WIP add benchmark.md
* add mmocr already
* add retina
* add mask rcnn none
* update mmdet benchmark
* fill mmcls benchmark
* add mmocr and mmedit
* add some mmseg benchmark of cpu
* add all data
* add platform
* remove mmseg mmedit ncnn and dbnet ncnn
* fix grammar typo
* fix comments
* fix typo
2021-12-24 10:39:31 +08:00
4bb37c54a2
Fix logo and intro ( #334 )
...
* crop logo
* fix README_zh-CN.md
* remoe empty files
2021-12-23 20:14:35 +08:00
e37ce3cf28
[Doc]: MMDet benchmark ( #265 )
...
* add mmdet benchmark
* fix docs
* fix docs
* fix docs
* add fp16
* add some int8 model
* add yolov3 benchmark
* add some benchmark
* fix docs
* add comment about mask-rcnn
* fix mmdet docs
* add ppl benchmark
* refactor benchmark
* refactor format
* add fcos and atss fp16
* fix benchmark
* fix mmdet docs
* fix docs
* fix docs
* fix docs
* add cn benchmark about mmdet
2021-12-23 17:42:14 +08:00
VVsssssk
RunningLeon
Johannes L
hanrui1sensetime
Semyon Bevzyuk
lzhangzz
Yifan Zhou
Echo-minn
q.yao
AllentDan
Haian Huang(深度眸)
StephenFang
Zhiqiang Wang
lvhan028
q.yao