medalotte
commented
2 years ago Dockerfile が用意されているのでこれを使用しようと思ったが、コンテナ内に clone している ByteTrack リポジトリのコミットハッシュが古い（更新されてない）。
RUN git clone https://github.com/ifzhang/ByteTrack \
&& cd ByteTrack \
&& git checkout 3434c5e8bc6a5ae8ad530528ba8d9a431967f237 \
&& mkdir -p YOLOX_outputs/yolox_x_mix_det/track_vis \
&& sed -i 's/torch>=1.7/torch==1.9.1+cu111/g' requirements.txt \
&& sed -i 's/torchvision==0.10.0/torchvision==0.10.1+cu111/g' requirements.txt \
&& sed -i "s/'cuda'/0/g" tools/demo_track.py \
&& pip3 install pip --upgrade \
&& pip3 install -r requirements.txt -f https://download.pytorch.org/whl/torch_stable.html \
&& python3 setup.py develop \
&& pip3 install cython \
&& pip3 install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI' \
&& pip3 install cython_bbox gdown \
&& ldconfig \
&& pip cache purgehttps://github.com/ifzhang/ByteTrack/blob/8d52fbdf9cd03757d8dd02c0631e526d164bd726/Dockerfile#L24
&& git checkout 3434c5e8bc6a5ae8ad530528ba8d9a431967f237
を
&& git checkout 8d52fbdf9cd03757d8dd02c0631e526d164bd726
に置き換えた上で以下のコマンドでビルド、コンテナを起動した。
$ docker build -t bytetrack:latest .
(略)
$ mkdir -p pretrained && \
> mkdir -p YOLOX_outputs && \
> xhost +local: && \
> docker run --gpus all -it --rm \
> -v $PWD/pretrained:/workspace/ByteTrack/pretrained \
> -v $PWD/datasets:/workspace/ByteTrack/datasets \
> -v $PWD/YOLOX_outputs:/workspace/ByteTrack/YOLOX_outputs \
> -v /tmp/.X11-unix/:/tmp/.X11-unix:rw \
> --device /dev/video0:/dev/video0:mwr \
> --net=host \
> -e XDG_RUNTIME_DIR=$XDG_RUNTIME_DIR \
> -e DISPLAY=$DISPLAY \
> --privileged \
> bytetrack:latest
non-network local connections being added to access control list
=====================
== NVIDIA TensorRT ==
=====================
NVIDIA Release 21.09 (build 26679335)
NVIDIA TensorRT 8.0.3 (c) 2016-2021, NVIDIA CORPORATION. All rights reserved.
Container image (c) 2021, NVIDIA CORPORATION. All rights reserved.
https://developer.nvidia.com/tensorrt
This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
To install Python sample dependencies, run /opt/tensorrt/python/python_setup.sh
To install the open-source samples corresponding to this TensorRT release version run /opt/tensorrt/install_opensource.sh.
To build the open source parsers, plugins, and samples for current top-of-tree on master or a different branch, run /opt/tensorrt/install_opensource.sh -b <branch>
See https://github.com/NVIDIA/TensorRT for more information.
ERROR: This container was built for NVIDIA Driver Release 470.57 or later, but
version 465.19.01 was detected and compatibility mode is UNAVAILABLE.
[[System has unsupported display driver / cuda driver combination (CUDA_ERROR_SYSTEM_DRIVER_MISMATCH) cuInit()=803]]
user@Obelisk-Desktop:/workspace/ByteTrack$ エラーが出てる。
ERROR: This container was built for NVIDIA Driver Release 470.57 or later, but version 465.19.01 was detected and compatibility mode is UNAVAILABLE.
使ってるマシンの NVIDIA Driver のバージョンが古いっぽい。
とりあえず無視して動かしてみる。
ByteTrack の公開実装を動かしてみる。
ここでは 2021/12/19 時点の main ブランチの HEAD (8d52fbdf) で確認を行う。
https://github.com/ifzhang/ByteTrack/tree/8d52fbdf9cd03757d8dd02c0631e526d164bd726