update

2026-09-11 00:22:49 -05:00 · 2023-02-05 00:25:04 +08:00
parent ebe5d3c90e
commit 6ee3697841
4 changed files with 26 additions and 27 deletions
--- a/docs/hardware/en/maixIII/ax-pi/flash_system.md
+++ b/docs/hardware/en/maixIII/ax-pi/flash_system.md
@@ -682,7 +682,8 @@ This is a demo for testing camera, visit [built in application](#built-in-applic
 - os04a10（Night enhanced camera）

 ```bash
-sample_vin_vo -c 2 -e 1 -s 0 -v dsi0@480x854@60
+sample_vin_vo -c 2 -e 1 -s 0 -v dsi0@480x854@60 # For gc4653 camera
+# sample_vin_vo -c 0 -e 1 -s 0 -v dsi0@480x854@60 # For os04a10 camera
 ```

 ![video](./../../../zh/maixIII/assets/video.jpg)
--- a/docs/hardware/en/maixIII/ax-pi/python_api.ipynb
+++ b/docs/hardware/en/maixIII/ax-pi/python_api.ipynb
@@ -106,7 +106,7 @@
   "id": "existing-output",
   "metadata": {},
   "source": [
-    "To run Jupyter Notebook on **AXera-Pi**, we need to get the IP address of **AXera-Pi**, both RNDIS IP address or network IP address are OK, with this we can open the Jupyter Notebook website application run on **AXera-Pi**. Run `ifconfig` to get the IP address of **AXera-Pi**, then run command `jupyter notebook` on **AXera-Pi** via a terminal, visit the `IP:8888` in your computer browser (Attention：`lo:127.0.0.1` is normally inaccessible), like `192.168.0.125:8888` (`192.168.0.125` is the example IP address of **AXera-Pi**, see the following picture), then you can run your python code on Jupyter Notebook.\n",
+    "To run Jupyter Notebook on **AXera-Pi**, we need to get the IP address of **AXera-Pi**, both RNDIS IP address or network IP address are OK, with this we can open the Jupyter Notebook website application run on **AXera-Pi**. Run `ifconfig` to get the IP address of **AXera-Pi**, then run command `jupyter notebook` on **AXera-Pi** via a terminal, visit the `IP:8888` in your computer browser (Attention：`lo:127.0.0.1` is normally inaccessible), like `192.168.0.125:8888` (`192.168.0.125` is a example IP address of **AXera-Pi**, see the following picture), then you can run your python code on Jupyter Notebook.\n",
    "\n",
    "![api_adb-2.jpg](attachment:api_adb-2.jpg)\n",
    "\n",
@@ -186,9 +186,9 @@
    "- **v：** Paste cell table\n",
    "- **dd：** Delete this cell table\n",
    "- **ii：** Stop running task\n",
-    "- **A：** Add cell table above\n",
-    "- **B：** Add cell table below\n",
-    "- **M：** Change cell table into markdown format"
+    "- **a：** Add cell table above\n",
+    "- **b：** Add cell table below\n",
+    "- **m：** Change cell table into markdown format"
   ]
  },
  {
@@ -377,19 +377,16 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "organic-charm",
   "metadata": {},
   "source": [
    "## ax-pipeline-api\n",
    "\n",
-    "[**ax-pipeline-api：**](https://github.com/junhuanchen/ax-pipeline-api)此项目基于 [ax-pipeline](https://github.com/AXERA-TECH/ax-pipeline) 适配实现 Python API 编程，用户可使用 Python 调用内置的多种 AI 模型以及通用的 Python 库 pinpong、opencv、numpy、pillow 等，让 AXera-Pi 用起来更简单！\n",
+    "[**ax-pipeline-api：**](https://github.com/junhuanchen/ax-pipeline-api) is based on [ax-pipeline](https://github.com/AXERA-TECH/ax-pipeline), it's used for Python API programming, with which users can load many built-in AI models by Python, or use python library like pinpong、opencv、numpy、pillow. This make AXera-Pi easilier to use.\n",
    "\n",
-    "使用 `ax-pipeline-api` 之前先做好以下准备工作：\n",
-    "\n",
-    "- 安装获取 `ax-pipeline-api` 包\n",
-    "\n",
-    "因 `ax-pipeline-api` 更新升级较频繁，用户在使用 Python 编程前可先在终端使用下方命令行更新包，确保自己使用是最新版本的即可。"
+    "Before using `ax-pipeline-api`, make sure you have installed it. And if you have trouble running with this application, update this application maybe a good solvment."
   ]
  },
  {
@@ -414,15 +411,14 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "weird-implementation",
   "metadata": {},
   "source": [
-    ">如果出现更新失败，可替换清华源 `-i https://pypi.tuna.tsinghua.edu.cn/simple` 加速一下。\n",
+    "Finishing installing or updating `ax-pipeline-api`, run `yolo5vs` model to have a try.\n",
    "\n",
-    "把 `ax-pipeline-api` 包升级好后，接下来我们先跑个 `yolo5vs` 模型实现目标检测！\n",
-    "\n",
-    "## 调用 yolov5s 实现目标检测 "
+    "## Object detection with yolov5s"
   ]
  },
  {
@@ -467,17 +463,18 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "static-netscape",
   "metadata": {},
   "source": [
-    "从上面跑的 yolov5s 模型示例来看，运行时编辑框下会打印输出目标检测的相关结果参数，而实际画面可在板卡屏幕上查看。我们也可以从上面的代码中替换掉不同功能的 `.so` 库或者是更换不同效果的 `AI` 模型来实现更多的 AI 应用。\n",
+    "As the log of running yolov5s above, object detection result parameters are printed out. And the detection picture is shown onboard screen.\n",
    "\n",
-    ">更换 `.so` 库以及更换 `AI` 模型请参考以下示例进行修改，这篇文档只挑选部分经典模型作为示例，大家可以举一反三进行更换功能库以及模型。所有示例都使用 `GC4653` 摄像头如有 OS04A10 型号请前往 [Maix-III 系列 AXera-Pi 常见问题（FAQ）](https://wiki.sipeed.com/hardware/zh/maixIII/ax-pi/faq_axpi.html)修改。\n",
+    "We can also using different `.so` library or other `AI` models to do more AI usages.\n",
    "\n",
-    "- 以下是内置的 libxxx*.so 库总览：\n",
+    "> All examples in this document are run on `GC4653` camera sensor, visit [Maix-III AXera-Pi (FAQ)](https://wiki.sipeed.com/hardware/en/maixIII/ax-pi/faq_axpi.html) to see how to switch camera sensor if you use `OS04A10` night enhanced camera sensor.\n",
    "\n",
-    "**可通过替换不同的 `libxxx*.so` 来选择更换不同的功能。**\n",
+    "- Here are the `ibxxx*.so` library in AXera-Pi:\n",
    "\n",
    "```bash\n",
    "libsample_h264_ivps_joint_vo_sipy.so            # input h264 video to ivps joint output screen vo\n",
@@ -489,9 +486,9 @@
    "libsample_vin_ivps_joint_vo_h265_sipy.so        # input mipi sensor to ivps joint output screen vo and save h265 video file\n",
    "```\n",
    "\n",
-    "**更换 `libxxx*.so` 可参考以下示例：**\n",
+    "This is the main code of changing `ibxxx*.so`.\n",
    "\n",
-    "```bash\n",
+    "```python\n",
    "    pipeline.load([\n",
    "        'libsample_vin_ivps_joint_venc_rtsp_vo_sipy.so',\n",
    "        '-p', '/home/config/yolov5s.json',\n",
@@ -499,9 +496,7 @@
    "    ])\n",
    "```\n",
    "\n",
-    "- 以下是内置的多种 AI 模型总览：\n",
-    "\n",
-    "**AI 模型被内置在 `/home/config` 的目录下，可更换不用模型来实现不同的 AI 应用。**\n",
+    "- Here are the AI models (which are in the folder `/home/config`) in AXera-Pi:\n",
    "\n",
    "```bash\n",
    "ax_bvc_det.json              hrnet_pose_yolov8.json           yolov5s_face_recognition.json\n",
@@ -517,9 +512,9 @@
    "hrnet_pose_ax_det.json\t      yolov5s_face.json\n",
    "```\n",
    "\n",
-    "**更换 AI 模型可参考以下示例：**\n",
+    "This is the main code of changing `AI models`.\n",
    "\n",
-    "``` bash\n",
+    "```python\n",
    "pipeline.load([\n",
    "    'libsample_vin_ivps_joint_vo_sipy.so',\n",
    "    '-p', '/home/config/yolov5s_face.json',\n",
@@ -529,11 +524,12 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "controlled-hands",
   "metadata": {},
   "source": [
-    "## 调用 yolov5s_face 实现人脸检测"
+    "## FAce dectection on yolov5s_face"
   ]
  },
  {
--- a/docs/hardware/en/maixzero/sense/start.md
+++ b/docs/hardware/en/maixzero/sense/start.md
@@ -264,6 +264,7 @@ The demo of uf2 format which can be burned to M0sense by u-disk is in the uf2_de

 1. Compiling your own firmware conversion application if it's the first time compiling.
 2. Everytime compiling the firmware, make sure you have [set the toolcahin path](#set-toolcahin-path)
+3. If failing to compile SDK. make sure the compiling command is `./build.sh m0sense_apps/blink/blink_baremetal`, not `./build.sh m0sense_apps/blink/blink_baremetal/` (Pay attention to the `/` in the end)

 ## Burn bin file

--- a/docs/hardware/zh/maixzero/sense/start.md
+++ b/docs/hardware/zh/maixzero/sense/start.md
@@ -265,6 +265,7 @@ gcc -I libs/uf2_format misc/utils/uf2_conv.c -o uf2_convert # 编译出固件转

 1. 第一次搭建环境最好自己编译一份 uf2 文件转换工具
 2. 每次新开终端编译记得配置一下 [编译工具链路径](#配置编译工具链路径)
+3. SDK 编译失败时确定自己是按照 [编译 demo](#编译-demo) 里面所说的使用 `./build.sh m0sense_apps/blink/blink_baremetal` 命令来执行编译的，而不是 `./build.sh m0sense_apps/blink/blink_baremetal/` （注意结尾处的 `/` ）命令

 ## 烧录 bin 文件