OpenMMLab Model Deployment Framework
 
 
 
 
 
 
Go to file
Yifan Zhou 7e8154090a
align mmedit static cfg (#82)
2021-09-16 19:55:07 +08:00
.github/workflows remove unused flag, fix lint 2021-06-29 10:23:52 +08:00
backend_ops [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +08:00
configs align mmedit static cfg (#82) 2021-09-16 19:55:07 +08:00
docs [Feature] Refactor v1 (#56) 2021-09-01 15:43:49 +08:00
mmdeploy remove mmocr redundant (#83) 2021-09-16 17:24:12 +08:00
requirements [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +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 [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +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
.pylintrc add pylintrc (#81) 2021-09-16 11:04:56 +08:00
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
MANIFEST.in [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +08:00
README.md [Docs] Add docs of ncnn deployment (#33) 2021-08-10 17:04:58 +08:00
requirements.txt [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +08:00
setup.cfg
setup.py [Refactor] Refactor config v1 (#80) 2021-09-16 10:26:09 +08:00

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