mirror of
https://github.com/open-mmlab/mmdeploy.git
synced 2025-01-14 08:09:43 +08:00
* 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
…
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
Description
OpenMMLab Model Deployment Framework
computer-visiondeep-learningdeploymentmmdetectionmmsegmentationmodel-converterncnnonnxonnxruntimeopenvinopplnnpytorchsdktensorrt
Readme
187 MiB
Languages
Python
46.6%
C++
41.3%
Cuda
4.4%
CMake
2%
C#
1.9%
Other
3.8%