OpenMMLab Model Deployment Framework
 
 
 
 
 
 
Go to file
hanrui1sensetime 667318c268
[Fix] mmdet bugs recover (#64)
* support ncnn mmdet fcos.py

* support fsaf

* fix_lint

* fix yapf

* fix clang-format

* fix bugs

* to master

* Fix topk 2-2

recover 2 input 2 output version to support mmdet

* Fix FCN Argmax adaptive output

* Add comments for adaptive output
2021-09-09 13:44:55 +08:00
.github/workflows remove unused flag, fix lint 2021-06-29 10:23:52 +08:00
backend_ops [Fix] mmdet bugs recover (#64) 2021-09-09 13:44:55 +08:00
configs [Feature] Add ppl backend for ocr edit and seg (#58) 2021-09-07 15:40:43 +08:00
docker add docker (#15) 2021-07-13 08:45:42 +00:00
docs [Feature] Refactor v1 (#56) 2021-09-01 15:43:49 +08:00
mmdeploy Test ops (#48) 2021-09-08 13:42:15 +08:00
tests Test ops (#48) 2021-09-08 13:42:15 +08:00
third_party [Feature] Add TensorRT batched NMS support (#3) 2021-06-25 19:31:16 +08:00
tools value=-1 as default (#59) 2021-09-06 10:27:53 +08:00
.gitignore
.gitmodules [Feature] Add TensorRT batched NMS support (#3) 2021-06-25 19:31:16 +08:00
.isort.cfg [Feature] Refactor v1 (#56) 2021-09-01 15:43:49 +08:00
.pre-commit-config.yaml
CMakeLists.txt [Feature] Merge NCNN deployment to grimoire based on mmcls - revert [#25](https://github.com/grimoire/deploy_prototype/pull/25) (#30) 2021-08-05 14:06:47 +08:00
LICENSE
README.md [Docs] Add docs of ncnn deployment (#33) 2021-08-10 17:04:58 +08:00
setup.cfg
setup.py

README.md

MMDeployment

Installation

  • Build backend ops

    • update submodule

      git submodule update --init
      
    • Build with onnxruntime support

      mkdir build
      cd build
      cmake -DBUILD_ONNXRUNTIME_OPS=ON -DONNXRUNTIME_DIR=${PATH_TO_ONNXRUNTIME} ..
      make -j10
      
    • Build with tensorrt support

      mkdir build
      cd build
      cmake -DBUILD_TENSORRT_OPS=ON -DTENSORRT_DIR=${PATH_TO_TENSORRT} ..
      make -j10
      
    • Build with ncnn support

      mkdir build
      cd build
      cmake -DBUILD_NCNN_OPS=ON -DNCNN_DIR=${PATH_TO_NCNN} ..
      make -j10
      
    • Or you can add multiple flags to build multiple backend ops.

  • Setup project

    python setup.py develop
    

Usage

python ./tools/deploy.py \
    ${DEPLOY_CFG_PATH} \
    ${MODEL_CFG_PATH} \
    ${MODEL_CHECKPOINT_PATH} \
    ${INPUT_IMG} \
    --work-dir ${WORK_DIR} \
    --device ${DEVICE} \
    --log-level INFO