10 Commits

Author SHA1 Message Date
tripleMu
031e7450bc
[Happy New Year] TensorRT + DeepStream Support. (#485)
* [Happy New Years] TensorRT + DeepStream Support.

* Add deepstream config

* pre-commit fix

* Fix name

* [Happy New Years] TensorRT + DeepStream Support.

* Add deepstream config

* pre-commit fix

* Fix name

* Add config

* Add rtmdet deepstream
2023-02-08 11:07:46 +08:00
tripleMu
4a7228a5cc
Fix rtmdet decoder in easydeploy (#519) 2023-02-07 14:45:27 +08:00
tripleMu
feef44da23
[Fix] Fix requirement about only ONNXRuntime without TensorRT (#469)
* Fix requirement about only onnxruntime without tensorrt

* Update projects/easydeploy/model/backendwrapper.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update projects/easydeploy/model/backendwrapper.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update projects/easydeploy/model/backendwrapper.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update projects/easydeploy/model/backendwrapper.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
2023-01-16 19:36:49 +08:00
Range King
e66991fc6e
[Fix] Fix YOLOv8 graph and a lint issue (#459)
* add missing bg frame

* fix easydeploy lint
2023-01-12 16:00:46 +08:00
tripleMu
8e39252259
Support YOLOv8 deploy (#456) 2023-01-12 10:07:44 +08:00
tripleMu
f1855ca618
[Feature] Add new YOLOX bbox coder for TensorRT-8 and fix TensorRT-7 bug (#450)
* Add yolox bbox decoder for tensorrt backend

* Fix tensorrt7+ bug
2023-01-11 17:10:04 +08:00
tripleMu
28439f102a
[Deploy] Support YOLOv7 easy deploy (#427)
* Support YOLOv7 easy deploy

* Remove useless comment

* Fix mkdir
2023-01-04 20:10:58 +08:00
tripleMu
a44495868d
[Feature] Support PyTorch model forward for TensorRT inference (#377)
* Support pytorch model forward for TensorRT

* Add ort wrapper

* Fix import

* Add deploy image-demo

* raise NotImplementedError

* Fix onnxruntime output gpu tensor
2022-12-29 12:11:16 +08:00
tripleMu
6fd50af6ab
Export onnx for model only (#361)
* Support export onnx for model only

* Fix

* Fix
2022-12-13 15:06:59 +08:00
tripleMu
1045b41b68
[Deploy] MMYOLO model convert to onnx for deployment. (#279)
* Fromat code

* Support ONNXRUNTIME

* Support mmyolo model convert to onnx for deploy.

* Same as dev branch

* Support yolox focus rewrite

* Support GConv Focus

* Update mmyolo/easydeploy/backbone/focus.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Add TensorRT build/infer Wrapper

* Add image_demo for deploy model

* Fix

* Merge dev

* Remove image-demo

* Roll back to dev

* Support model switch to deploy

* Remove --deploy

* Add new deploy method

* Format code and add doc

* Move md to project

* add readme and readme_zh to easy_deploy

* Update projects/easydeploy/README_zh-CN.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* Update projects/easydeploy/README.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: xin-li-67 <williamlee.xin@gmail.com>
Co-authored-by: Xin Li <7219519+xin-li-67@users.noreply.github.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
2022-11-23 10:43:41 +08:00