AllentDan
5fdd75fba1
Add tensorrt int8 and fp16 configs for all the rest codebases ( #152 )
...
* add configs for all codebases except mmocr and fixed some bugs
* add ocr det
* add fp16 and int8 config for text recog
2021-10-27 15:59:02 +08:00
Yifan Zhou
227bebaade
[Enhancement]: Rename files in mmdeploy/core/rewriters ( #157 )
...
* Rename files
* lint
* update docstring
2021-10-27 15:12:00 +08:00
q.yao
c8b78f6c9b
Add citation ( #151 )
...
* Add citation
* fix typo
2021-10-27 15:03:40 +08:00
q.yao
6c420dcd05
Remove useless files ( #156 )
2021-10-27 14:50:12 +08:00
RunningLeon
0b46c505ee
[Docstring] Update docstring and its config ( #142 )
...
* update
* fix lint
* add config for interrogate
* remove config
* solve comments
2021-10-27 10:44:54 +08:00
AllentDan
77131ea071
[Feature] Add exporting SARNet to onnxruntime backends. ( #134 )
...
* save codes
* save codes
* support sar exporting to onnxruntime and tensorrt
* use 4G max gpu space
* support sequential sar
* remove trt config for sar
* add sar unit tests
* add sar unit tests
* resolve conflicts
* remove torch.add rewrite in unit tests
2021-10-26 15:42:06 +08:00
Yifan Zhou
398bf2b386
[Refactor]: Refactor mmdeploy/core ( #140 )
...
* refactor function rewriter
* Pass unit test
* Fix test
* Fix test
* lint
* refactor function rewriter
* Pass unit test
* Fix test
* Fix test
* lint
* support openvino
* update
1. All type hints of cfg are set to Dict
2. Check if kwargs exist when calling patch_model
3. Complement tests
4. key name 'object' is set to '_object'
* lint
* Update docstring
* Fix tests
* Improve test
2021-10-26 10:30:14 +08:00
AllentDan
35b7341766
fix mmocr ( #147 )
2021-10-25 19:09:28 +08:00
hanrui1sensetime
9e227b228b
[UnitTest] mmocr unittest ( #130 )
...
* WIP test_mmocr 8 out of 20
* test_mmocr_export
* test mmocr apis
* add test data
* add mmocr model unittest 5 passed 1 failed
* finish mmocr unittest
* fix lint
* fix yapf
* fix isort
* fix flake8
* fix docformatter
* fix docformatter
* try to fix unittest after merge master
* Change test.py for backend.DEFAULT
* fix flake8
* fix ut
* fix yapf
* fix ut build
* fix yapf
* fix mmocr_export ut
* fix mmocr_apis ort not cuda
* remove explicit .forward
* remove backendwrapper
* simplify the crnn and dbnet config
* simplify instance_test.json
* add another case of decoder
* increase coverage of test_mmocr_models base_recognizer
* improve coverage
* improve encode_decoder coverage
* reply for grimoire codereview
* what if not check cuda?
* remove image data
* reply to runningleon code review
* fix fpnc
* fix lint
* try to fix CI UT error
* fix fpnc with and wo custom ops
* fix yapf
* skip fpnc when cuda is not ready in ci
* reply for code review
* reply for code review
* fix yapf
* reply for code review
* fix yapf
* fix conflict
* remove unmatched data path
* remove unnecessary comments
2021-10-25 10:15:57 +08:00
Semyon Bevzyuk
c5a87fb1bc
[Enhancement]: OpenVINO deployment support for some models ( #117 )
...
* Fix include and lib paths for onnxruntime.
* Fixes for SSD export test
* Add onnx2openvino and OpenVINODetector. Test models: ssd, retinanet, fcos, fsaf.
* Add support for two-stage models: faster_rcnn, cascade_rcnn
* Add doc
* Add strip_doc_string for openvino.
* Fix openvino preprocess.
* Add OpenVINO to test_wrapper.py.
* Fix
* Add openvino_execute.
* Removed preprocessing.
* Fix onnxruntime cmake.
* Rewrote postprocessing and forward, added docstrings and fixes.
* Added device type change to OpenVINOWrapper.
* Update forward_of_single_roi_extractor_dynamic_openvino and fix doc.
* Update docs.
* Add OpenVINODetector and onn2openvino tests.
* Add input_info to onnx2openvino.
* Add TestOpenVINOExporter and test_single_roi_extractor.
* Moved get_input_shape_from_cfg to openvino_utils.py and added test.
* Added test_cascade_roi_head.
* Add backend.check_env() to tests.
* Add OpenVINO to get_rewrite_outputs and to some tests in test_mmdet_models.
* Moved test_single_roi_extractor to test_mmdet_models.
* Removed TestOpenVINOExporter.
2021-10-21 16:07:35 +08:00
Yifan Zhou
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
Yifan Zhou
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
Yifan Zhou
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
AllentDan
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
q.yao
f56a30025a
[Enhance] Add spell hook ( #116 )
...
* add spell hook
* fix code spell
2021-10-09 11:34:14 +08:00
q.yao
a335444a49
[Fix]: Remove TensorRT NMS plugin ( #113 )
...
* Remove TensorRT NMS plugin
* remove nms test
2021-10-09 11:14:38 +08:00
VVsssssk
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
RunningLeon
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
AllentDan
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
AllentDan
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
AllentDan
9b070a5dda
[Enhancement] Refine mmcls rewriting ( #106 )
...
* fix mmcls head
* fix lint
2021-09-28 19:21:51 +08:00
RunningLeon
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
RunningLeon
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
Yifan Zhou
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
VVsssssk
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
q.yao
b8217d8243
[Doc] Add docstring & type hint of mmdeploy/core ( #92 )
2021-09-26 20:03:39 +08:00
hanrui1sensetime
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
RunningLeon
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
RunningLeon
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
q.yao
5453f9befa
[Feature] Add tensorrt single stage partition ( #88 )
...
* Add tensorrt single stage partition
* add docstring&typehint
2021-09-23 15:49:36 +08:00
AllentDan
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
AllentDan
5e3288e74d
remove mmocr redundant ( #83 )
2021-09-16 17:24:12 +08:00
q.yao
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
hanrui1sensetime
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
AllentDan
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
VVsssssk
00bfbf8e89
Test ops ( #48 )
...
* test_ops_v1
* test_ops_version1.0
* test_ops_version1.1
* test_ops_version1.1
* test_ops_version1.1
* test_ops1.1
* test_ops2.0
* test_ops2.1
* test_ops2.1
* test_ops2.1
* test_ops2.1
* test_ops2.2
* test_ops2.2
* test_ops2.3
* test_ops2.3
* test_ops2.3
* test_ops2.3
* test_2.4
* test_ops2.4
2021-09-08 13:42:15 +08:00
AllentDan
3975d491d5
[Feature] Add ppl backend for ocr edit and seg ( #58 )
...
* add ppl for ocr edit and seg
* remove random crop after update mmedit
2021-09-07 15:40:43 +08:00
hanrui1sensetime
56bc1242b2
[Feature] Add NCNN on MMSegmentation ( #55 )
...
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add calib data generator
* create calib dataset
* finish end2end int8
* add split two stage tensorrt visualize
* first
* fix0
* fix1
* dirty work
* wip
* add allocator
* finally done!
* lint
* fix lint
* better gather
* better onnx2ncnn
* fix tensorslice bugs
* fix lint
* fix clang-format
* remove comments
* fix expand
* int param
* fix lint
* [Fix] NCNN TensorSlice op bugs (#42 )
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add calib data generator
* create calib dataset
* finish end2end int8
* add split two stage tensorrt visualize
* fix tensorslice bugs
* fix lint
* fix clang-format
* remove comments
* int param
* fix lint
Co-authored-by: grimoire <yaoqian@sensetime.com>
* add two stage ncnn support
* remove unused ops
* git unused config
* remove no_grad, should add in refactor
* add ncnn wrapper
* fix lint
* size return tuple
* Resolve grammar error
* Fix lint
* Trim Trailing Whitespace
* fix trim
* add argmax to topk
* add ArgMax parse
* add ncnn mmseg deploy cfg
* utils add ncnn mmseg
* add ncnn
* fix lint
* fix yapf
* fix clang-format-9
* remove debugging code
Co-authored-by: grimoire <yaoqian@sensetime.com>
Co-authored-by: grimoire <streetyao@live.com>
Co-authored-by: maningsheng <mnsheng@yeah.net>
2021-09-03 15:19:54 +08:00
q.yao
e73d9fb50b
[Feature] Add mmocr ncnn support ( #53 )
...
* first
* fix0
* fix1
* dirty work
* wip
* add allocator
* finally done!
* lint
* fix lint
* better gather
* better onnx2ncnn
* fix expand
* [Fix] NCNN TensorSlice op bugs (#42 )
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add calib data generator
* create calib dataset
* finish end2end int8
* add split two stage tensorrt visualize
* fix tensorslice bugs
* fix lint
* fix clang-format
* remove comments
* int param
* fix lint
Co-authored-by: grimoire <yaoqian@sensetime.com>
* add two stage ncnn support
* remove unused ops
* git unused config
* remove no_grad, should add in refactor
* add ncnn wrapper
* fix lint
* size return tuple
* Resolve grammar error
* Fix lint
* Trim Trailing Whitespace
* fix trim
* update wrapper
* remove logs
* remove
* csrc optimize
* add ncnn dbnet support
* finish crnn support
* add comment
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
2021-09-03 15:16:20 +08:00
q.yao
2b98040b26
[Feature] Refactor v1 ( #56 )
...
* [Refactor] add enum class and use functions to get configuration (#40 )
* add task and codebase enum class
* use funcitons to get config
* Refactor wrappers of mmcls and mmseg (#41 )
* move wrappers of cls & det to apis
* remove get_classes_from_config
* rename onnx_helper to onnx_utils
* move import to outside of class
* refactor ortwrappers
* Refactor build dataset and dataloader for mmseg (#44 )
* refactor build_dataset and build_dataloader for mmcls and mmseg
* remove repeated classes
* set build_dataloader with shuffle=False
* [Refactor] pplwrapper and mmocr refactor (#46 )
* add
* add pplwrapper and refactor mmocr
* fix lint
* remove unused arguments
* apply dict input for pplwrapper and ortwrapper
* add condition before import ppl and ort stuff
* update ppl (#51 )
* Refactor return value and extract_model (#54 )
* remove ret_value
* refactor extract_model
* fix typo
* resolve comments
* [Refactor] Refactor model inference pipeline (#52 )
* move attribute_to_dict to extract_model
* simplify the inference and visualization
* remove unused import
* [Feature] Support SRCNN in mmedit with ONNXRuntime and TensorRT (#45 )
* finish mmedit-ort
* edit __init__ files
* add noqa
* add tensorrt support
* 1. Rename "base.py"
2. Move srcnn.py to correct directory
* fix bugs
* remove figures
* align to refactor-v1
* update comment in srcnn
* fix lint
* newfunc -> new_func
* Add visualize.py
split visualize() in each codebase
* fix lint
* fix lint
* remove unnecessary code in ORTRestorer
* remove .api
* edit super(), remove dataset
* [Refactor]: Change name of split to partition (#57 )
* refactor mmcls configs
* refactor mmdet configs and split params
* rename rest split to partition from master
* remove base.py
* fix init of inference class
* fix mmocr init, add show_result alias
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
Co-authored-by: RunningLeon <maningsheng@sensetime.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
2021-09-01 15:43:49 +08:00
q.yao
823ca38646
[Feature] Add NCNN mmdetection support ( #49 )
...
* first
* fix0
* fix1
* dirty work
* wip
* add allocator
* finally done!
* lint
* fix lint
* better gather
* better onnx2ncnn
* fix expand
* [Fix] NCNN TensorSlice op bugs (#42 )
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add calib data generator
* create calib dataset
* finish end2end int8
* add split two stage tensorrt visualize
* fix tensorslice bugs
* fix lint
* fix clang-format
* remove comments
* int param
* fix lint
Co-authored-by: grimoire <yaoqian@sensetime.com>
* add two stage ncnn support
* remove unused ops
* git unused config
* remove no_grad, should add in refactor
* add ncnn wrapper
* fix lint
* size return tuple
* Resolve grammar error
* Fix lint
* Trim Trailing Whitespace
* fix trim
* update wrapper
* remove logs
* remove
* csrc optimize
Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com>
2021-08-26 18:40:14 +08:00
AllentDan
8fe8056080
[Feature] Add trt ort mdcn plugins ( #43 )
...
* add trt mdcn plugin
* add onnxruntime mdcn op
* add mdcn trt ort plugins
* fix lint
* remove comment
* remove plugin condition lines
* apply new form
* use serialized_size
2021-08-25 10:17:21 +08:00
RunningLeon
e5dc959276
[Feature]: Support PSPNet with static shape in ORT and TRT ( #39 )
...
* support pspnet with static shape
* set default as None to --test-img
2021-08-20 13:39:03 +08:00
q.yao
fd40119694
[Feature] TensorRT int8 support ( #35 )
...
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add func mark count dict
* use assert_cfg_valid
* update func count before add Mark
* fix dynamic shape support
* add calib data generator
* create calib dataset
* finish end2end int8
* add split two stage tensorrt visualize
2021-08-19 12:56:00 +08:00
AllentDan
7c465654b9
[Feature] Add dbnet18 and crnn support ( #36 )
...
* add mmocr
re-orgnize codes
save codes
save codes
save codes
add dbnet18
* fix lint
* support crnn
* fix lint
* resolve comments
* resolve conflicts
* resolve module registry error
* test
* resolve comments
* fix lint
* use algrithm_type and add dataset evaluation
* suit newest mmocr
* fix lint and remove trt version check
2021-08-19 11:53:00 +08:00
Yifan Zhou
1ba7e526c1
[FIX] ONNXRuntime bug when detecting empty picture ( #37 )
...
* [Feature] Add test tool to evaluate backend models on det and cls datasets (#26 )
* add test tool and re-orgnize apis.utils
* handle topk and refine codes
* add cls export and test support
* fix lint
* move ort into wrapper
* resolve conflicts
* resolve comments
* resolve conflicts
* resolve comments and padding mrcnn
* resolve comments
* Fix: [0, ...] tensor bug
* check the format
Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com>
Co-authored-by: zhouyifan <PJLAB\zhouyifan@shai14001077l.pjlab.org>
2021-08-17 09:59:08 +08:00
q.yao
4c8c34d354
[Feature] Enable faster rcnn split onnxruntime ( #27 )
...
* fix custom ops support, fix multiple mark bug, add name mapping
* check if the value_info need to be added
* remove unnecessary print
* add nms implement
* two stage split wip
* add two stage split
* add split retinanet visualize
* add two stage split (wip)
* finish two stage split
* fix lint
* move parse string to mmdeploy.utils
* add func mark count dict
* use assert_cfg_valid
* update func count before add Mark
* fix dynamic shape support
2021-08-13 10:06:28 +08:00
hanrui1sensetime
f8b62ae4d0
[Feature] Support NCNN inference tests ( #34 )
...
* add inference test
* fix for review comments
* add inference test results table
* fix grammer errors
* fix typo
2021-08-12 17:38:38 +08:00
RunningLeon
7dbc12d23f
[Feature]: Support FCN,DeeepLabV3, DeepLabV3Plus in mmseg with ONNXRuntime and TensorRT ( #31 )
...
* fix mask empty result
* support fcn exporting to ONNX for ort and trt in whole mode
* resolve comments
* remove unnecessary code
* update prepare_input
* rewrite psp_head & aspp_head
* test fcn deeplabv3 deeplabv3plus with trt
2021-08-12 16:44:16 +08:00
AllentDan
dcb88e4439
[Feature] Add ppl backend. ( #32 )
...
* add ppl support
* save
* add ppl speed test
* drop "add ppl speed test"
This reverts commit 467504a23074a2defdadeff9819c8d19bfefda71.
* add ppl backend
* resolve comments
* fix baseDeployClassifier
2021-08-12 14:44:10 +08:00
