4c1f62f3cb
Remove GPU CI ( #138 )
...
* remove config of gpu
* remove empty line
2021-10-19 20:29:19 +08:00
fd75d57175
[Unittest]: Add MMSegmentation test ( #125 )
...
* add ncnn test exporter in test_ops.py
* add ncnn test exporter in utils.py
* add onnxruntime and tensorrt ops test
* fix blank line
* fix comment
add nms ops test
* remove nms test
* add test sample
add dockerstring
* remove nms test
* fix grid_sample
add type hind
* fix problem
* fix dockerstring
* add nms batch_nms multi_level_roi_align
* add test data
* fix problem
* rm pkl file dependent
* rm file
* add docstring
* remove multi_level_dependce
* add mmseg module unittest
* add mmseg test
* add mmseg model unit test
* fix blankline
* rename file
* add syncbn2bn unit test
* add apis/export
* lint
* lint
* ??
* delete#
* fix ncnn check
* fix problems
* fix problems
* fix dim problems
* resolve comments
* Fix SwitchBackendWrapper
* fix assert problems
* fix assert
* Remove comment
* merge master
Co-authored-by: SingleZombie <singlezombie@163.com>
2021-10-19 15:25:06 +08:00
6f36717a72
[Unittest]: Test mmdeploy.pytorch ( #133 )
...
* add some tests
* Fix topk bug
* Fix bug in test
* Add remaining tests
* Remvoe debug code
* Delete redundant code
* Remove redundant code
2021-10-19 13:14:33 +08:00
0f1cda0d3e
[Unittest]Add mmcv unit test ( #128 )
...
* add ncnn test exporter in test_ops.py
* add ncnn test exporter in utils.py
* add onnxruntime and tensorrt ops test
* fix blank line
* fix comment
add nms ops test
* remove nms test
* add test sample
add dockerstring
* remove nms test
* fix grid_sample
add type hind
* fix problem
* fix dockerstring
* add nms batch_nms multi_level_roi_align
* add test data
* fix problem
* rm pkl file dependent
* rm file
* add docstring
* remove multi_level_dependce
* add mmseg module unittest
* add mmseg test
* add mmseg model unit test
* fix blankline
* rename file
* add syncbn2bn unit test
* add apis/export
* lint
* lint
* ??
* delete#
* fix ncnn check
* fix problems
* fix problems
* add mmcv unit test
* add mmcv unit test
* modify scores
* fix format
* fix scores to rand
* remove blank line
Co-authored-by: SingleZombie <singlezombie@163.com>
2021-10-19 11:43:35 +08:00
fef9d9e651
[Docs]: Add how_to_support_new_model document ( #123 )
...
* Add how_to_support_new_model document
* update follow comments
* fix for comment
* rename
2021-10-18 11:08:27 +08:00
26cf2bdf05
[Enhancement]: Clarify the return value of get_rewrite_outputs ( #129 )
...
* Modify function and its call
* fix typo
2021-10-15 16:18:32 +08:00
2bd67527d5
[Docs]: Add readme zn-cn ( #126 )
...
* add readme zn-cn
* update punctuation
2021-10-15 11:52:53 +08:00
10c4ef4203
[Unittest]: MMEdit unittest ( #124 )
...
* add mmedit test
* Solve unittest bug
* lint
* Remove debug code
* add data
* Refine code
* Fix ci
* Fix ci
* follow changes in mmdet test
* try to remove pytest skip
* remove redundant code
* rename
* Fix type hint
* Fix lint
* Refine SwitchBackendWrapper. Fix type hint
* update docstring
2021-10-15 10:25:48 +08:00
07cb78bb7c
[Unittest] add ncnn unittest expand and fix expand.cpp bugs. ( #118 )
...
* add ncnn unittest expand
* rollback utils.py
* remove figures
2021-10-14 10:24:14 +08:00
d4828c7836
[Unittests] MMDet unittests ( #112 )
...
* add mmdet unittests
* remove redundant img meta info
* import wrapper from backend util
* force add wrapper
* use smaller nuance
* add seed everything
* add create input part and some inference part unittests
* fix lint
* skip ppl
* remove pyppl
* add dataset files
* import ncnn_ext inside ncnn warpper
* use cpu device to create input
* add pssd and ptsd unittests
* clear mmdet unittests
* wrap function to enable rewrite
* refine codes and resolve comments
* move mmdet inside test func
* remove redundant line
* test visualize in mmdeploy.apis
* use less memory
* resolve comments
* fix ci
* move pytest.skip inside test function and use 3 channel input
2021-10-13 17:24:11 +08:00
6fdf6b8616
apply cmake-format and refactor cmake scripts of building onnx and te… ( #99 )
...
* apply cmake-format and refactor cmake scripts of building onnx and tensorrt ops
* add static target
* suppress 'CMAKE_CUDA_ARCHITECTURES' warning when cmake with version 18 or later is used
* fix typo
2021-10-13 16:42:11 +08:00
1ed6bc0fb5
refactor ncnn ops unittest ( #121 )
2021-10-12 14:24:56 +08:00
46e0a3abc6
[Documentation] add ncnn backend docs ( #122 )
...
* add ncnn backend docs
* remove fix version
* reply for code review
2021-10-12 14:24:33 +08:00
997f8dd9a9
add pylint score ( #119 )
...
* add pylint score
* add sc file
* Update build.yml
* Update build.yml
* Update build.yml
* auto load config file
2021-10-11 14:52:19 +08:00
d136001aa6
rewrited->rewritten ( #120 )
2021-10-09 14:19:12 +08:00
1d47688b32
[Docs]: Add sphinx document ( #109 )
...
* Add document structure
* better zh_cn document
* add build example, update requirement
* add readme
* add usage
* fix end of file
* fix codebase names, add TODO
2021-10-09 14:10:42 +08:00
21f2b047a1
[Unittest] Test ncnn gather op and fix gather.cpp ( #114 )
...
* add shape constantofshape unittest for ncnn
* fix lint
* standarize import
* fix lint
* reply for code review
* reply for code review
* fix lint
* remove some hardcode
* fix lint
* reply for code review
* test gather and fix gather cpp code
* fix yapf
* fix clang-format
* reply for code review
* reply for code review
* fix lint
2021-10-09 14:06:49 +08:00
f8a70f1d33
[Unittest]: Complement remaining tests in apis/core/utils ( #110 )
...
* Add remaining tests
* Use another method to import
* try to fix ppl import error
* try to fix pyppl import bug 2
* try to fix pyppl import error 3
* try to fix pyppl import error 4
* Use test class
* remove ()
* lint
* add else branch
2021-10-09 14:05:48 +08:00
cba43e4c22
[Unittest] Add NCNN tensorslice unittest and fix tensorslice.cpp bugs. ( #115 )
...
* add tensorslice unittest
* reply code review
* fix lint
* fix typo
2021-10-09 11:42:32 +08:00
f56a30025a
[Enhance] Add spell hook ( #116 )
...
* add spell hook
* fix code spell
2021-10-09 11:34:14 +08:00
a335444a49
[Fix]: Remove TensorRT NMS plugin ( #113 )
...
* Remove TensorRT NMS plugin
* remove nms test
2021-10-09 11:14:38 +08:00
43eee77fdd
[Unittest]Add ops test ( #108 )
...
* add ncnn test exporter in test_ops.py
* add ncnn test exporter in utils.py
* add onnxruntime and tensorrt ops test
* fix blank line
* fix comment
add nms ops test
* remove nms test
* add test sample
add dockerstring
* remove nms test
* fix grid_sample
add type hind
* fix problem
* fix dockerstring
* add nms batch_nms multi_level_roi_align
* add test data
* fix problem
* rm pkl file dependent
* rm file
* add docstring
* remove multi_level_dependce
* Update test_ops.py
2021-10-09 10:45:03 +08:00
de9498a8f2
[Enhance]: Add more docstring. ( #111 )
...
* add docstring for apis
* add simple docstring for mmdet
* add simple docstring for mmseg
* add simple docstring for mmcls
* add simple docstring for mmedit
* add simple docstring for mmocr
* add simple docstring for rewriting
* update thresh for docstring coverage
* update
* update docstring
* solve comments
* remove unrelated symbol
2021-09-29 15:59:38 +08:00
4587322441
[Fix] fix the bug of mmocr visualizing ( #105 )
...
* fix mmcor show image
* remove rescale in ocr recognition
2021-09-29 15:04:32 +08:00
6318e9fcf9
[Unittest] Add ncnn 'Shape' 'ConstantOfShape' unittest ( #107 )
...
* add shape constantofshape unittest for ncnn
* fix lint
* standarize import
* fix lint
* reply for code review
* reply for code review
* fix lint
* remove some hardcode
* fix lint
* reply for code review
2021-09-29 15:02:58 +08:00
be2df638b1
less deprecated warning when compile tensorrt ops ( #103 )
2021-09-29 10:49:44 +08:00
5818095fe0
[Unittests] Add a demo for codebase rewrite part unittests ( #89 )
...
* save codes
* add test_model
* save codes
* wrap func
* reformat
* fix lint
* refine docstring
* remove pkl in .gitignore
* add pkl
* apply channel 3
* add function and trt backend rewrite unittest
* fix lint and typo
* add skip condition
* fix typo
* define deploy config inside func and keep ortwrapper original
* speed up and remove ctx
* only inference if no backends
* fix ci
* fix ci
* [Fix] Fix test_calibration (#101 )
* fix test calibration
* Modify cuda to cpu
* add tensorrt check
* Revert "[Fix] Fix test_calibration (#101 )"
This reverts commit 3f8b8384bfd880538050798d2567f1c137a36174.
Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
2021-09-28 19:29:58 +08:00
9b070a5dda
[Enhancement] Refine mmcls rewriting ( #106 )
...
* fix mmcls head
* fix lint
2021-09-28 19:21:51 +08:00
8633993ca3
[Feature]: Add cuda11.1 CI ( #104 )
...
* add cuda11.1 config
* add onnx
* update
* remove onnx
* lock mmcls version
2021-09-28 16:52:21 +08:00
0bef0513c6
[Unittest]: Add ncnn test exporter and topk test ( #84 )
...
* add ncnn test exporter in test_ops.py
* add ncnn test exporter in utils.py
* fix ncnn unittest
* fix lint
* fix lint
* fix lint isort
* remove ncnn roi_align pytest
* add ncnn topk unittest
* update to new api
* fix lint
* add comments
* skip class
* skip ncnn
Co-authored-by: hanrui1sensetime <hanrui1@sensetime.com>
Co-authored-by: maningsheng <mnsheng@yeah.net>
2021-09-28 14:20:04 +08:00
2073f3327e
[Fix] Fix test_calibration ( #101 )
...
* fix test calibration
* Modify cuda to cpu
2021-09-27 19:51:07 +08:00
6ba1d45e81
[Fix]: fix ignoring test_ops ( #102 )
...
* show message from pytest skip
* skip utility class
Co-authored-by: SingleZombie <singlezombie@163.com>
2021-09-27 19:10:18 +08:00
f9b2cab3fa
[Feature]: Update github CI ( #100 )
...
* align mmedit static cfg
* add for test
* update requirments
* add dependencies from mmlab
* change name
* lower thresh for interrogate at first
* update test
* update to skip
* Move import tensorrt
* Move import statement
Co-authored-by: SingleZombie <singlezombie@163.com>
2021-09-27 17:43:41 +08:00
09be668a27
[Docstring]: Update docstring for codebase ( #95 )
...
* align mmedit static cfg
* add docstring for mmcls
* update
* update for mmdet
* update for mmseg
* update for mmocr
* resolve comments
* add doc for mmedit
* add docstring for mmcls
* update
* update for mmdet
* update for mmseg
* update for mmocr
* add doc for mmedit
* resolve comments
* resolve comments
* add type hint
* resolve comments
* resolve comments
Co-authored-by: SingleZombie <singlezombie@163.com>
2021-09-27 17:30:30 +08:00
4de5bbb461
[Unittest]: Add demos for core/apis/utils ( #91 )
...
* add unittests
* lint
* modify .gitignore, remove useless files
* remove emtpy.py and generate it when use
* Update according to comments
1. Use tempfile
2. Delete inference test (which will be tested in each codebase)
3. Refine calibration test
* update annotation
* Add export_info
* Reduce data scale, fix assert
* update json blank line
* add backend check
2021-09-27 16:10:47 +08:00
b6c16d01db
[Unittest]: Add onnxruntime and tensorrt ops unit test ( #96 )
...
* add ncnn test exporter in test_ops.py
* add ncnn test exporter in utils.py
* add onnxruntime and tensorrt ops test
* fix blank line
* fix comment
add nms ops test
* remove nms test
* add test sample
add dockerstring
* remove nms test
* fix grid_sample
add type hind
* fix problem
* fix dockerstring
2021-09-27 11:16:23 +08:00
067b915383
fix void pointer arithmetic ( #98 )
2021-09-27 10:52:26 +08:00
b8217d8243
[Doc] Add docstring & type hint of mmdeploy/core ( #92 )
2021-09-26 20:03:39 +08:00
01e2240b94
[Fix] Fix RoiAlign Unittest ( #90 )
...
* fix roi_align unittest
* fix lint
* remove non must code
* fix isort
* reply for review
* fix lint
* reply code review
* fix docformatter
* fix review
* reuse mmcv.roialignfunction
2021-09-26 11:21:18 +08:00
5b8750b83b
[Enhance]: Logging trace info for debugging in deploy tool ( #93 )
...
* print trace info for debugging
* resolve comment
2021-09-24 19:09:39 +08:00
de096d5f00
[Docstring]: Coding style and docstring revision for mmdeploy.apis ( #87 )
...
* check style of mmdeploy.apis.ncnn
* finish check style with mmdeploy.apis.onnxruntime
* check mmdeploy.apis.ppl
* check mmdeploy.apis.tensorrt
* update docstring for mmdeploy.apis
* update some docstring
* make style consistent
* update
* resolve comments
* resolve comments
2021-09-24 10:40:39 +08:00
5453f9befa
[Feature] Add tensorrt single stage partition ( #88 )
...
* Add tensorrt single stage partition
* add docstring&typehint
2021-09-23 15:49:36 +08:00
ec66d47057
[Feature] Add speed test components ( #86 )
...
* add time counter
* add time-count to all backends
* fix lint
* add docstring and unit tests
* use test instead
* remove enable member
* refinement
* replace runtime error with assert and log speed with a single line
* fix unit tests
* resolve comments and add file output
* remove an argument
2021-09-22 19:42:16 +08:00
7e8154090a
align mmedit static cfg ( #82 )
2021-09-16 19:55:07 +08:00
5e3288e74d
remove mmocr redundant ( #83 )
2021-09-16 17:24:12 +08:00
30a56be6ff
add pylintrc ( #81 )
2021-09-16 11:04:56 +08:00
4c0b36b7ff
[Refactor] Refactor config v1 ( #80 )
...
* [Refactor] Refactor configs according to new standard (#67 )
* modify cfg and cfg_util
* modify tensorrt config
* fix bug
* lint
* Fix
1. Delete print
2. Modify the return value from "False, None" to "None" and related code
3. Rename 2 get functions
* modify apply_marks
* [Feature] Refactor ocr config (#71 )
* add text detection config refactor
* add text recognition refactor
* add static exporting for mmocr
* fix lint
* set max space in child config
* use Sequence[int] instead
* add assert input_shape
* fix static bug and add ppl ort and trt static (#77 )
* [Feature] Refine setup.py (#61 )
* add setup.py and related files
* lint
* Edit requirements
* modify onnx version
* modify according to comments
* [Refactor] Refactor mmseg configs (#73 )
* refactor mmseg config
* change create_input
* fix lint
* fix lint
* fix lint
* fix yapf
* fix yapf
* update export
* remove Segmentation
* remove tast assert
* add onnx_config
* remove hardcode
* Inherit with static
* Remove blank line
* Add segmentation task enum
* add assert task
* mmocr version 0.3.0 (#79 )
* add dump_info
* [Feature]: Refactor config in mmdet (#75 )
* support onnxruntime
* add two stage
* test two-stage ort and ppl
* update fcos post_params
* fix calib
* test ok with maskrcnn dynamic
* add empty line
* add static into config filename
* add input_shape to create_input in mmdet
* add static to some configs
* remove todo codes
* remove partition config in base
* refactor create_input
* rename task name in mmdet
* return None if input_shape is None
* add size info into mmdet configs filenames
* reorganize mmdet configs
* add object detection task for mmdet
* rename get_mmdet_params
* keep naming style consistent
* update post_params for fcos
* fix typo in ncnn config
* [Refactor] Refactor mmedit static config (#78 )
* add static cfg
* update create_input
* [Refactor]: Refactor mmcls configs (#74 )
* refactor mmcls2.0
* fix classify_tensorrt_dynamic.py
* fix classify_tensorrt_dynmic.py
* classify_tensorrt_dynamic_int8.py
* fix file name
* fix ncnn ppl
* updata prepare_input.py
* update utils.py
* updata constant.py
* add
* fix prepare_input.py
* fix prepare_input.py
* add static config file
* add blank lines
* fix prepare_input.py(wait test)
* fix input_shape(wait test)
* Update prepare_input.py
* fix classification_tensorrt_dynamic(wait test)
* fix classification_tensorrt_dynamic_int8(wait test)
* fix classification_tensorrt_static_int8(wait test)
* Rename classification_tensorrt_dynamic.py to classification_tensorrt_dynamic-224x224-224x224.py
* Rename classification_tensorrt_dynamic_int8.py to classification_tensorrt_dynamic_int8-224x224-224x224.py
* Rename classification_tensorrt_dynamic_int8-224x224-224x224.py to classification_tensorrt_int8_dynamic_224x224-224x224.py
* Rename classification_tensorrt_dynamic-224x224-224x224.py to classification_tensorrt_dynamic_224x224-224x224.py
* Rename classification_tensorrt_static.py to classification_tensorrt_static_224x224.py
* Rename classification_tensorrt_static_int8.py to classification_tensorrt_int8_static_224x224.py
* Update prepare_input.py
* Rename classification_tensorrt_dynamic_224x224-224x224.py to classification_tensorrt_dynamic-224x224-224x224.py
* Rename classification_tensorrt_int8_dynamic_224x224-224x224.py to classification_tensorrt_int8-dynamic_224x224-224x224.py
* Rename classification_tensorrt_int8-dynamic_224x224-224x224.py to classification_tensorrt_int8_dynamic-224x224-224x224.py
* Rename classification_tensorrt_int8_static_224x224.py to classification_tensorrt_int8_static-224x224.py
* Rename classification_tensorrt_static_224x224.py to classification_tensorrt_static-224x224.py
* Update prepare_input.py
* Update prepare_input.py
* Update prepare_input.py
* Update prepare_input.py
* Update prepare_input.py
* Update prepare_input.py
* Update prepare_input.py
* change logging msg
Co-authored-by: maningsheng <mnsheng@yeah.net>
* fix
* fix else branch
* fix bug for trt in mmseg
* enable dump trt info
* fix trt static for mmdet
* remove two-stage_partition_tensorrt_static-800x1344 config
* fix wrong backend in ppl config
* fix partition calibration
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
Co-authored-by: RunningLeon <maningsheng@sensetime.com>
Co-authored-by: VVsssssk <88368822+VVsssssk@users.noreply.github.com>
Co-authored-by: maningsheng <mnsheng@yeah.net>
Co-authored-by: AllentDan <AllentDan@yeah.net>
2021-09-16 10:26:09 +08:00
aba6ad5da7
[Feature] Support FCOS and FSAF for mmdetection ncnn deployment ( #63 )
...
* support ncnn mmdet fcos.py
* support fsaf
* fix_lint
* fix yapf
* fix clang-format
* Delete output_ncnn.jpg
* Delete output_pytorch.jpg
* remove comments and fix typo
* fix blank line
* Fix typo
* Remove unnessisary comments
* Add comment
* Add comments
2021-09-14 20:10:18 +08:00
10793f488e
[Feture] Export preprocess and deploy information to SDK ( #65 )
...
* add export info
* add dump-info funciton
* add collect info
* fix lint
* add docstring
* docstring
* docstring
2021-09-13 18:50:29 +08:00
745c51f965
[Fix] Remove dockerfile ( #69 )
2021-09-10 17:58:07 +08:00
RunningLeon
VVsssssk
Yifan Zhou
q.yao
hanrui1sensetime
AllentDan
lvhan028