Skip to content

Latest commit

 

History

History
39 lines (32 loc) · 2.14 KB

README.md

File metadata and controls

39 lines (32 loc) · 2.14 KB
Raw

OpenPose Dockerfiles

CPU + Python API + CUDA + cuDNN (./Dockerfile)

CMake also seems to have issues with building to support CMake, which the work here seems to fix - however, it targets a now depreciated version of nvidia/cuda. By changing the target from nvidia/cuda:11.4.0-cudnn8-devel-ubuntu18.04 to nvidia/cuda:11.3.1-cudnn8-devel-ubuntu18.04, it now has a functional source image.

CPU + Python API (./Dockerfile-CPU)

The above with some removed dependencies for GPU support, namely the usage of caffe-cpu instead of libcaffe-cuda-dev.

Example Usage

Pull it in the following manner:

docker pull ghcr.io/hiibolt/igait-openpose

Then, start it with the following command:

docker run -it --rm --gpus all --security-opt=label=disable ghcr.io/hiibolt/igait-openpose

Run an example inference:

./build/examples/openpose/openpose.bin --image_dir /openpose/examples/media --display 0 --write_images /output_images

Please note that in order for this to work, you will need to have the NVIDIA Container Toolkit installed.

Expected Behaviour

CPU

  • With the above example usage commands, a body pose skeleton should be mapped onto each output image image
  • You may expect a significantly slower experience compared to CUDA acceleration, which OpenPose will warn you of. If you intend to only use CPU, you may safely discard this error.

CUDA

  • Running nvidia-smi should display readily available GPUs. image
  • Running an inference should debug output the availability and usage of at least one GPU image
  • With the above example command, a body pose skeleton should be mapped onto each output image image

Developed by @hiibolt on GitHub