update readme

README.md

@@ -22,15 +22,18 @@ docker run -it --name=mobilenetv2 --network=host --ipc=host --shm-size=16g --dev
 ```shell
 git clone --recursive http://developer.hpccube.com/codes/modelzoo/mobilenetv2_mmcv.git 
 cd mobilenetv2_mmcv/mmpretrain-mmcv 
+pip install -e .
 pip install -r requirements.txt
 ```
 
 ### Dockerfile（方法二）
 
-    cd mobilenetv2_mmcv/docker
-    docker build --no-cache -t mobilenetv2_mmcv:latest .
-    docker run -it --name=mobilenetv2 --network=host --ipc=host --shm-size=16g  --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --privileged --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /opt/hyhal:/opt/hyhal:ro -v $PWD/mobilenetv2_mmcv:/home/mobilenetv2_mmcv <your IMAGE ID> bash
-    # 若遇到Dockerfile启动的方式安装环境需要长时间等待，可注释掉里面的pip安装，启动容器后再安装python库：pip install -r requirements.txt
+    cd mmpretrain/docker
+    docker build --no-cache -t mmpretrain:latest .
+    docker run -it --name=mobilenetv2 --network=host --ipc=host --shm-size=16g  --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --privileged --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /opt/hyhal:/opt/hyhal:ro -v $PWD/mmpretrain:/home/mmpretrain <your IMAGE ID> bash
+    pip install -e .
+    # 若遇到Dockerfile启动的方式安装环境需要长时间等待，可注释掉里面的pip安装，启动容器后再安装python库：
+    pip install -r requirements.txt
 
 ### Anaconda（方法三）
 
@@ -45,8 +48,22 @@ torchvision==0.16.0+das1.1.git7d45932.abi1.dtk2404.torch2.1 mmcv==2.0.1+das1.1.g
 
 Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应
 
-2、其它非特殊库参照requirements.txt安装
-    pip install -r requirements.txt
+2、安装mmpretrain仓库源码
+
+```shell
+cd mmpretrain
+
+pip install -e .
+```
+
+3、其它非特殊库参照requirements.txt安装
+
+```shell
+pip install -r requirements.txt
+```
+
+
+
 
 ## 示例
 
@@ -63,5 +80,3 @@ bash tools/dist_train.sh resnet50-test.py 8
 ```shell
 bash tools/dist_train.sh <配置文件脚本> <训练用卡数>
 ```
-
-

docker/Dockerfile

-ARG PYTORCH="1.12.1"
-ARG CUDA="11.3"
-ARG CUDNN="8"
-
-FROM pytorch/pytorch:${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel
-
-# fetch the key refer to https://forums.developer.nvidia.com/t/18-04-cuda-docker-image-is-broken/212892/9
-RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/3bf863cc.pub 32
-RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub
-
-ENV TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0+PTX"
-ENV TORCH_NVCC_FLAGS="-Xfatbin -compress-all"
-ENV CMAKE_PREFIX_PATH="(dirname(which conda))/../"
-
-RUN apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libsm6 libxrender-dev libxext6 \
-    && apt-get clean \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install MIM
-RUN pip install openmim
-
-# Install MMPretrain
-RUN conda clean --all
-RUN git clone https://github.com/open-mmlab/mmpretrain.git
-WORKDIR ./mmpretrain
-RUN mim install --no-cache-dir -e .
+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:pytorch:2.1.0-ubuntu20.04-dtk24.04.1-py3.10
+ENV DEBIAN_FRONTEND=noninteractive
+# 安装pip相关依赖
+COPY requirements.txt requirements.txt
+RUN pip3 install -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com -r requirements.txt

docker/requirements.txt

+albumentations>=0.3.2 --no-binary qudida,albumentations
+colorama
+requests
+rich
+scipy
+matplotlib>=3.1.0
+numpy
+packaging
+codecov
+flake8
+interrogate
+isort==4.3.21
+pytest
+xdoctest >= 0.10.0
+yapf

docker/serve/Dockerfile

-ARG PYTORCH="2.0.1"
-ARG CUDA="11.7"
-ARG CUDNN="8"
-FROM pytorch/torchserve:latest-gpu
-
-ARG MMPRE="1.2.0"
-
-ENV PYTHONUNBUFFERED TRUE
-
-ENV HOME="/home/model-server"
-ENV PATH="/opt/conda/bin:$HOME/.local/bin:$PATH"
-RUN export FORCE_CUDA=1
-
-# TORCHSEVER
-RUN pip install torchserve torch-model-archiver
-RUN pip install nvgpu
-
-# OPEN-MMLAB
-ARG PYTORCH
-ARG CUDA
-RUN pip install openmim
-RUN mim install mmpretrain==${MMPRE}
-RUN mkdir -p $HOME/tmp
-
-COPY --chown=model-server entrypoint.sh $HOME/.local/bin/entrypoint.sh
-
-RUN chmod +x $HOME/.local/bin/entrypoint.sh
-
-COPY --chown=model-server config.properties $HOME/config.properties
-
-EXPOSE 8080 8081 8082
-
-USER model-server
-WORKDIR $HOME
-ENV TEMP=$HOME/tmp
-ENTRYPOINT ["/home/model-server/.local/bin/entrypoint.sh"]
-CMD ["serve"]

docker/serve/config.properties

-inference_address=http://0.0.0.0:8080
-management_address=http://0.0.0.0:8081
-metrics_address=http://0.0.0.0:8082
-model_store=/home/model-server/model-store
-load_models=all

docker/serve/entrypoint.sh

-#!/bin/bash
-set -e
-
-if [[ "$1" = "serve" ]]; then
-    shift 1
-    torchserve --start --ts-config /home/model-server/config.properties
-else
-    eval "$@"
-fi
-
-# prevent docker exit
-tail -f /dev/null