fix: docker image name from sdk package

- none

Change-Id: If3e3a06b96edac864fb94a9829e621e0998d54db

Author: charlesxzb

docs/developer_manual/source_en/02_environment.rst

@@ -41,8 +41,7 @@ If you are using docker for the first time, you can execute the following comman
 Make sure the installation package is in the current directory, and then create a container in the current directory as follows:
 
 .. code-block:: shell
-
-  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4 # without 'sophgo' if you use image from SDK package
   # "myname" is just an example, you can use any name you want
   # use --privileged to get root permission, if you don't need root permission, please remove this parameter
 

docs/developer_manual/source_zh/02_environment.rst

@@ -46,7 +46,7 @@ TPU-MLIR在Docker环境开发, 配置好Docker就可以编译和运行了。
 
 .. code-block:: shell
 
-  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4 # 如果是SDK包中获取的镜像则没有sophgo前缀
   # myname只是举个名字的例子, 请指定成自己想要的容器的名字
   # 使用 --privileged 参数以获取root权限，如果不需要root权限，请删除该参数
 

docs/quick_start/source_en/02_env.rst

@@ -32,13 +32,14 @@ If you are using docker for the first time, you can execute the following comman
 
 .. _docker container_setup:
 
-If you download the image file, make sure the image file is in the current directory, and then create a container in the current directory as follows:
+You can get the docker image file from the SDK package. If you download the image file, make sure the image file is in the current directory, and then create a container in the current directory as follows:
 
 
 .. code-block:: shell
 
   # use --privileged to get root permission, if you don't need root permission, please remove this parameter
-  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+  $ docker load -i tpuc_dev_v3.4.tar.gz
+  $ docker run --privileged --name myname -v $PWD:/workspace -it tpuc_dev:v3.4
 
 where ``myname`` is the name of the container, which can be customized; ``$PWD`` is the current directory, synchronized with the container's ``/workspace`` directory.
 

docs/quick_start/source_en/Appx.04_modelzoo_test.rst

@@ -171,18 +171,18 @@ If you need precision test on BasicVSR, please download and unzip the Vid4 datas
 Prepare the toolchain compilation environment
 ~~~~~~~~~~~~~~~~~~
 
-It is recommended to use the toolchain software in a docker environment, see :ref:`Base environment configuration <docker configuration>` to install Docker. and execute the following commands in your working directory (the directory which ``model-zoo`` is located) to create a Docker container:
+It is recommended to use the toolchain software in a docker environment, see :ref:`Base environment configuration <docker configuration>` to install Docker. The docker image file can be obtained from the SDK package.Execute the following commands in your working directory (the directory which ``model-zoo`` is located) to create a Docker container:
 
 .. code-block:: shell
 
-   $ docker pull sophgo/tpuc_dev:v3.4
-   $ docker run --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+   $ docker load -i tpuc_dev_v3.4.tar.gz
+   $ docker run --name myname -v $PWD:/workspace -it tpuc_dev:v3.4
 
 If you want to keep the container after it exits, simply remove the ``--rm`` parameter:
 
 .. code-block:: shell
 
-   $ docker run --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4 --rm
+   $ docker run --name myname -v $PWD:/workspace -it tpuc_dev:v3.4 --rm
 
 After running the command, it will be in a Docker container. You can the latest ``tpu-mlir`` wheel installation package from the SDK package, such as ``tpu_mlir-*-py3-none-any.whl``. Install tpu_mlir in the Docker container:
 

docs/quick_start/source_zh/02_env.rst

@@ -32,12 +32,13 @@
 
 .. _docker container_setup:
 
-若下载镜像文件，则需要确保镜像文件在当前目录，并在当前目录创建容器如下:
+镜像文件可从SDK包中获取。若下载镜像文件，则需要确保镜像文件在当前目录，并在当前目录创建容器如下:
 
 .. code-block:: shell
 
   # 使用 --privileged 参数以获取root权限，如果不需要root权限，请删除该参数
-  $ docker run --privileged --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+  $ docker load -i tpuc_dev_v3.4.tar.gz
+  $ docker run --privileged --name myname -v $PWD:/workspace -it tpuc_dev:v3.4
 
 其中， ``myname`` 为容器名称，可以自定义； ``$PWD`` 为当前目录，与容器的 ``/workspace`` 目录同步。
 

docs/quick_start/source_zh/Appx.04_modelzoo_test.rst

@@ -173,18 +173,18 @@ Vid4 (可选)
 准备工具链编译环境
 ~~~~~~~~~~~~~~~~~~
 
-建议在 docker 环境使用工具链软件，可以参考 :ref:`基础环境配置 <docker configuration>` 安装Docker。并在工作目录（即 ``model-zoo`` 所在目录）下执行以下命令创建Docker容器：
+建议在 docker 环境使用工具链软件，可以参考 :ref:`基础环境配置 <docker configuration>` 安装Docker。并在工作目录（即 ``model-zoo`` 所在目录）。docker镜像文件可从SDK包中获取，执行以下命令创建Docker容器：
 
 .. code-block:: shell
 
-   $ docker pull sophgo/tpuc_dev:v3.4
-   $ docker run --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4
+   $ docker load -i tpuc_dev_v3.4.tar.gz
+   $ docker run --name myname -v $PWD:/workspace -it tpuc_dev:v3.4
 
 如果要让容器在退出后删除，可以添加 ``--rm`` 参数：
 
 .. code-block:: shell
 
-   $ docker run --name myname -v $PWD:/workspace -it sophgo/tpuc_dev:v3.4 --r
+   $ docker run --name myname -v $PWD:/workspace -it tpuc_dev:v3.4 --r
 
 
 运行命令后会处于Docker的容器中，从提供的SDK包中获取最新的 ``tpu-mlir`` wheel安装包，例如 ``tpu_mlir-*-py3-none-any.whl``。在Docker容器中安装TPU-MLIR: