Onnx-cpu docker image is incomplete

[octavflorescu]

[octav.florescu@internal-vm ~]$ echo $docker_image_name artifacts.codelinaro.org/codelinaro-aimet/aimet-dev:1.28.0.onnx-cpu [octav.florescu@internal-vm ~]$ docker run -p 9876:9876 --rm -it -u $(id -u ${USER}):$(id -g ${USER}) -v /etc/passwd:/etc/passwd:ro -v /etc/group:/etc/group:ro -v ${HOME}:${HOME} -v ${WORKSPACE}:${WORKSPACE} --entrypoint /bin/bash -w ${WORKSPACE} --hostname ${docker_container_name} ${docker_image_name}

octav.florescu@aimet-dev-octavf:/data/local/data/octavf/edge/aimet$ python3 Python 3.8.10 (default, May 26 2023, 14:05:08) [GCC 9.4.0] on linux Type "help", "copyright", "credits" or "license" for more information.

from aimet_onnx.cross_layer_equalization import equalize_model Traceback (most recent call last): File "", line 1, in ModuleNotFoundError: No module named 'aimet_onnx'

[octavflorescu]

same in parallel for torch_cpu/torch-cpu -> ModuleNotFoundError: No module named 'aimet_torch'

[octavflorescu]

not solved, but workaround:

export AIMET_VARIANT=onnx-gpu
export WORKSPACE=/data/local/data/octavf/edge/aimet/
export docker_image_name=artifacts.codelinaro.org/codelinaro-aimet/aimet-dev:1.28.0.${AIMET_VARIANT}
export docker_container_name=aimet-dev-octavf

docker ps -a | grep ${docker_container_name} && docker kill ${docker_container_name}

docker run -p 9876:9876 --rm -it -u $(id -u ${USER}):$(id -g ${USER}) \
-v /etc/passwd:/etc/passwd:ro -v /etc/group:/etc/group:ro \
-v ${HOME}:${HOME} -v ${WORKSPACE}:${WORKSPACE} \
--entrypoint /bin/bash -w ${WORKSPACE} --hostname ${docker_container_name} ${docker_image_name}

export AIMET_VARIANT=onnx_cpu
export release_tag=1.28.0
export download_url="https://github.com/quic/aimet/releases/download/${release_tag}"
export wheel_file_suffix="cp38-cp38-linux_x86_64.whl"
python3 -m pip install ${download_url}/AimetOnnx-${AIMET_VARIANT}_${release_tag}-${wheel_file_suffix} --user --no-deps


octav.florescu@aimet-dev-octavf:/data/local/data/octavf/edge/aimet$ python3
Python 3.8.10 (default, May 26 2023, 14:05:08)
[GCC 9.4.0] on linux
>>> from aimet_onnx.cross_layer_equalization import equalize_model
2023-09-14 10:32:12,675 - root - INFO - AIMET
>>>

[quic-mangal]

We will look into this. Thanks