ModelBox实战开发：RK3568实现摄像头虚拟背景

野性酷女 2023-10-12 18:06 34阅读 0赞

本文将使用ModelBox端云协同AI开发套件（RK3568）实现摄像头虚拟背景AI应用的开发。

![format_png][]

最终运行效果如下：

![16dc053d314419d6135369a7715389d3.png][]

### RK3568 ###

本应用采用RK开发套件完成，需要具备RK3568开发板。本硬件可以通过以下链接购买：[润和AI开发板\_【最新版】\_云商店-华为云][AI_-] ，规格包含：RK3568开发板×1、A2 WiFi模块×1、外壳×1、电源线和电源插头×1、散热片×1。

### 模型训练 ###

[Notebook:][Notebook]

![b68f7efd8e1480b714a6045e10b592d8.png][]

### 模型推理 ###

[Notebook:][Notebook 1]

![75bf5beba4268723d599b23120ba7a12.png][]

onnx结构：

![9e29f3ca971417e70aac7aa14a9f777a.png][]

### 模型转换 ###

[Notebook:][Notebook 2]

![4caec1f001752fb8140766f24846e12c.png][]

rknn结构：

![5e4432b90791b6bd9bec366e4eff87cf.png][]

### 原生onnxruntime推理 ###

我们准备了(1080p, 30fps)的视频，使用原生的onnxruntime进行推理，帧率最高是7：

实现代码：

![1744b6e36287a1a4e0133074243648f7.gif][]

"""
    OpenCV 读取摄像头视频视频流，使用原生的onnxruntime推理
    """
    # 导入OpenCV
    import cv2
    import time
    import drawUtils
    import numpy as np
    import onnxruntime
    # cap = cv2.VideoCapture(0)
    cap = cv2.VideoCapture('test.mp4')
    
    if not cap.isOpened():
     print('文件不存在或编码错误')
    else:
     i = 0
     fps = 30
     start_time = time.time()
     font = cv2.FONT_HERSHEY_PLAIN
     image_background = cv2.imread('R-C.jpg')
     width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     onnx_model = onnxruntime.InferenceSession('linknet.onnx')
     image_background = cv2.resize(image_background, (width, height))
     writer = cv2.VideoWriter('test_result.mp4',cv2.VideoWriter_fourcc(*'X264'),fps,(width,height))
     image_background = image_background/255.
    
    while cap.isOpened():
     ret,frame = cap.read()
     if ret:
     img = cv2.resize(frame, (256, 256))
     img = img[...,::-1]/255.
     img = img.astype(np.float32)
     img = np.transpose(img, (2, 0, 1))
     data = np.expand_dims(img, axis=0)
     onnx_input ={onnx_model.get_inputs()[0].name: data}
     pred_mask = onnx_model.run(None, onnx_input)
     pred_mask = np.array(pred_mask)
     pred_mask = pred_mask[0][0][0]
     pred_mask = cv2.resize(pred_mask, (width, height))
     pred_mask = pred_mask.reshape((height, width, 1))
     img_multi = pred_mask*frame/255.
     mask_layer = np.ones((height, width)).reshape(height, width, 1)-pred_mask
     mask_layer = image_background*mask_layer
     image_add = img_multi+mask_layer
     image_add = image_add*255
     image_add = image_add.astype(np.uint8)
     # 计算FPS
     i += 1
     now = time.time()
     fps_text = int(1 / ( now - start_time))
     start_time = now
     print('linknet post ' + str(i))
     # 添加中文（首先导入模块）
     img_add = drawUtils.cv2AddChineseText(image_add, '帧率：'+str(fps_text), (20,50), textColor=(0, 255, 0), textSize=30)
     # 显示画面
     # cv2.imshow('demo',img_add)
     writer.write(img_add)
     # 退出条件
     if cv2.waitKey(1) & 0xFF == ord('q'):
     break
     else:
     break
    
    cap.release()
    cv2.destroyAllWindows()

![5f99890f4d636326c8c5d16d8d2643f3.gif][]

修改使用编为0摄像头（默认为PC自带的摄像头）进行实时检测：

![7e3d65c17181f237882f3404f556fe3b.png][]

### ModelBox AI应用开发 ###

### 直接使用工程 ###

#### 1）下载案例 ####

本案例所需资源（代码、模型、测试数据等）均可从[网盘链接][Link 1]下载。

#### 2）运行应用 ####

将virtual\_background文件夹拖到工程目录workspace目录下面，开启性能统计：

![aa3dfc66dd3b42bc856d2f92f27d4881.png][]

切换到工程目录，执行bin/main.bat运行应用，生成的视频和性能统计文件都在hilens\_data\_dir文件夹下面：

![4afcf05edf902bd5c388852b0f7a80ce.png][]

#### 3）性能统计 ####

在Chrome浏览器chrome://tracing中加载性能统计文件：

![ffa1a508e6f9cd3c593af95919b7056c.png][]

该AI应用输入1080p的视频，batch\_size=4耗时约为256ms，平均每帧处理速度为64ms，fps=1000/64≈16，接下来我们给出该AI应用在ModelBox中的完整开发过程（以开发套件为例）。

#### 4）摄像头检测 ####

打开工程目录bin/mock\_task.toml文件，修改其中的任务输入和任务输出，配置为如下内容：

![9c82a465a7da1372cb33fdcb4f771f9f.gif][]

# 用于本地mock文件读取任务，脚本中已经配置了IVA_SVC_CONFIG环境变量, 添加了此文件路径
    ########### 请确定使用linux的路径类型，比如在windows上要用  D:/xxx/xxx  不能用D:\xxx\xxx  ###########
    # 任务的参数为一个压缩并转义后的json字符串
    # 直接写需要转义双引号， 也可以用 content_file 添加一个json文件，如果content和content_file都存在content会被覆盖
    # content_file支持绝对路径或者相对路径，不支持解析环境变量(包括${HILENS_APP_ROOT}、${HILENS_DATA_DIR}等)
    [common]
    content = "{\"param_str\":\"string param\",\"param_int\":10,\"param_float\":10.5}"
    # 任务输入配置，mock模拟目前仅支持一路rtsp或者本地url, 当前支持以下几种输入方式：
    # 1. rtsp摄像头或rtsp视频流：type="rtsp", url="rtsp://xxx.xxx"  (type为rtsp的时候，支持视频中断自动重连)
    # 2. 设备自带摄像头或者USB摄像头：type="url"，url="摄像头编号,比如 0 或者 1 等" (需配合local_camera功能单元使用)
    # 3. 本地视频文件：type="url"，url="视频文件路径" (可以是相对路径 -- 相对这个mock_task.toml文件, 也支持从环境变量${HILENS_APP_ROOT}所在目录文件输入)
    # 4. http服务：type="url", url="http://xxx.xxx"(指的是任务作为http服务启动，此处需填写对外暴露的http服务地址，需配合httpserver类的功能单元使用)
    # 5. 支持多输入[input] [input1] [input2] ...，对应的输出为[output] [output1] [output2] ...，如果使用videoout功能单元输出，则输入和输出个数必须匹配，同时url不能重名
    [input]
    type = "url"
    url = "0"
    #url = "../data/test.mp4"
    # 任务输出配置，当前支持以下几种输出方式：
    # 1. rtsp视频流：type="local", url="rtsp://xxx.xxx"
    # 2. 本地屏幕：type="local", url="0:xxx" (设备需要接显示器，系统需要安装桌面)
    # 3. 本地视频文件：type="local"，url="视频文件路径" (可以是相对路径——相对这个mock_task.toml文件, 也支持输出到环境变量${HILENS_DATA_DIR}所在目录或子目录)
    # 4. http服务：type="webhook", url="http://xxx.xxx" (指的是任务产生的数据上报给某个http服务，此处需填写上传的http服务地址)
    [output]
    type = "local"
    url = "0"
    #url = "../hilens_data_dir/test_result.mp4"

![e97a3bf3956fe5260de6edf622e31074.gif][]

执行.\\bin\\main.bat camera运行应用，将会自动弹出实时的人像分割画面：

![bd13ba30d7d12b8913b7ea93579f8f30.png][]

### 从零开发工程 ###

如果你对项目开发感兴趣，可以通过本章进一步了解。

#### 1）远程连接开发板 ####

我们推荐在PC端使用VS Code远程连接开发板来对设备进行操作，安装Remote-SSH：

![c6a4a17508e58ac81a9f821b9abf1a2d.png][]

#### 2）查看设备ip地址 ####

可以在APP应用智慧生活上查看设备的ip地址：

![format_png 1][]

#### 3）配置SSH连接 ####

电脑和设备处于同一WiFi下，在VS Code中使用Remote-SSH远程登陆：

![00662f66f30bd053ff242085d00c5024.png][]

### RK3568应用开发 ###

#### 创建工程 ####

在SDK目录下使用create.py脚本创建工程，我决定工程取名为virtual\_background：

rock@rock-3a:~$ cd /home/rock/modelbox
    rock@rock-3a:~/modelbox$ ./create.py -t server -n virtual_background
    sdk version is modelbox-rk-aarch64-1.5.3
    success: create virtual_background in /home/rock/modelbox/workspace

#### 创建推理功能单元 ####

rock@rock-3a:~/modelbox$ ./create.py -t infer -n linknet_infer -p virtual_background
    sdk version is modelbox-rk-aarch64-1.5.3
    success: create infer linknet_infer in /home/rock/modelbox/workspace/virtual_background/model/linknet_infer

可以看到推理功能单元创建在了项目工程的model目录下面：

![99e30018fe738d6dbda0debc1ce702f8.png][]

将我们转换好的模型linknet.rknn拖到linknet\_infer目录下，接着编辑.toml配置文件，主要修改模型的路径与输入输出，由于我们模型有一个来自rknpu的uint8的类型输入和一个float类型的输出，所以对配置文件编辑如下：

![82d320a4cfe1c426b2ca3746b3c7a1ca.gif][]

# Copyright (C) 2020 Huawei Technologies Co., Ltd. All rights reserved.
    [base]
    name = "linknet_infer"
    device = "rknpu"
    version = "1.0.0"
    description = "your description"
    entry = "./linknet.rknn" # model file path, use relative path
    type = "inference"
    virtual_type = "rknpu2" # inference engine type: rockchip now support rknpu, rknpu2(if exist)
    group_type = "Inference" # flowunit group attribution, do not change
    is_input_contiguous = "false" # rk do not support memory combine, fix, do not change
    # Input ports description
    [input]
    [input.input1]  # input port number, Format is input.input[N]
    name = "Input" # input port name
    type = "uint8" # input port data type ,e.g. float or uint8
    device = "rknpu" # input buffer type: use rknpu for zero-copy, cpu also allow
    # Output ports description
    [output]
    [output.output1] # output port number, Format is output.output[N]
    name = "Output" # output port name
    type = "float" # output port data type ,e.g. float or uint8

![5ed7b5c35b8559f61109ead4b4bd0f73.gif][]

可以看到该模型有1个输入节点，1个输出节点。需要注意其中的virtual\_type配置与npu类别有关，RK3568需配置为rknpu2；输入节点的device配置建议设为与该推理功能单元的上一个功能单元相同。

**ModelBox内置了rknn推理引擎和推理逻辑，开发者只需要准备好模型文件、编辑好配置文件，即可使用该模型进行推理，无需编写推理代码。**

另外，本案例使用的人像分割模型是由Pytorch框架训练得到，我们事先使用rknn-toolkit2工具将它转换为RK3568支持的模型格式，感兴趣的话可以在RK3568模型转换查看模型转换过程。

#### 创建后处理功能单元 ####

我们需要一个后处理功能单元来对模型推理结果进行解码，依然是万能的create.py脚本：

rock@rock-3a:~/modelbox$ ./create.py -t python -n linknet_post -p virtual_background
    sdk version is modelbox-rk-aarch64-1.5.3
    success: create python linknet_post in /home/rock/modelbox/workspace/virtual_background/etc/flowunit/linknet_post

可以看到在项目工程的etc/flowunit目录下面已经生成了该功能单元，存放.toml配置文件与.py功能代码文件：

![eadf9e51fb602aafa87c1b62cbcce555.png][]

接下来补充该功能单元的逻辑代码，如果对此不感兴趣，可以将我们资源包中的代码CtrlC+V速通本节。

首先补充后处理功能单元的配置文件，对于后处理功能单元，我们需要知道模型推理的shape，因此需要对config字段进行配置。此外，我们还需要修改输入输出，接收一个float类型的推理结果与一个uint8类型的原图，输出融合后的新图：

![c096133a24565025ef5c9f60f2914f65.gif][]

# Copyright (c) Huawei Technologies Co., Ltd. 2022. All rights reserved.
    # Basic config
    [base]
    name = "linknet_post" # The FlowUnit name
    device = "cpu" # The flowunit runs on cpu
    version = "1.0.0" # The version of the flowunit
    type = "python" # Fixed value, do not change
    description = "description" # The description of the flowunit
    entry = "linknet_post@linknet_postFlowUnit" # Python flowunit entry function
    group_type = "Generic" # flowunit group attribution, change as Input/Output/Image/Generic ...
    # Flowunit Type
    stream = false # Whether the flowunit is a stream flowunit
    condition = false # Whether the flowunit is a condition flowunit
    collapse = false # Whether the flowunit is a collapse flowunit
    collapse_all = false # Whether the flowunit will collapse all the data
    expand = false #  Whether the flowunit is a expand flowunit
    # The default Flowunit config
    [config]
    mask_h = 256
    mask_w = 256
    # Input ports description
    [input]
    [input.input1] # Input port number, the format is input.input[N]
    name = "in_mask" # Input port name
    type = "float" # Input port type
    [input.input2] # Input port number, the format is input.input[N]
    name = "in_image" # Input port name
    type = "uint8" # Input port type
    # Output ports description
    [output]
    [output.output1] # Output port number, the format is output.output[N]
    name = "out_image" # Output port name
    type = "uint8" # Output port type

![f6ae69cec8ca638a7b77822307de002d.gif][]

后处理代码：

![67c6563bdf7135d846a4473337849f71.gif][]

# Copyright (c) Huawei Technologies Co., Ltd. 2022. All rights reserved.
    #!/usr/bin/env python
    # -*- coding: utf-8 -*-
    import _flowunit as modelbox
    import numpy as np
    import cv2
    class linknet_postFlowUnit(modelbox.FlowUnit):
     # Derived from modelbox.FlowUnit
     def __init__(self):
     super().__init__()
     self.image_background = cv2.imread('data/R-C.jpg')
     self.image_background = cv2.cvtColor(self.image_background,cv2.COLOR_BGR2RGB)
     self.image_background = self.image_background/255.
     def open(self, config):
     # Open the flowunit to obtain configuration information
     self.mask_h = config.get_int('mask_h', 256)
     self.mask_w = config.get_int('mask_w', 256)
     self.index = 0 
     return modelbox.Status.StatusCode.STATUS_SUCCESS
     def process(self, data_context):
     # Process the data
     in_mask = data_context.input("in_mask")
     in_image = data_context.input("in_image")
     out_image = data_context.output("out_image")
     # linknet_post process code.
     # Remove the following code and add your own code here.
     for buffer_mask, buffer_image in zip(in_mask, in_image):
     # 获取输入Buffer的属性信息
     width = buffer_image.get('width')
     height = buffer_image.get('height')
     channel = buffer_image.get('channel')
     # 将输入Buffer转换为numpy对象
     image_background = cv2.resize(self.image_background, (width, height))
     mask_data = np.array(buffer_mask.as_object(), copy=False)
     mask_data = mask_data.reshape(self.mask_h, self.mask_w)
     mask_data = cv2.resize(mask_data, (width, height))
     mask_data = mask_data.reshape(height, width, 1)
     image_data = np.array(buffer_image.as_object(), dtype=np.uint8, copy=False)
     image_data = image_data.reshape(height, width, channel)
     img_multi = mask_data*image_data/255.
     mask_layer = np.ones((height, width))
     mask_layer = mask_layer.reshape(height, width, 1)
     mask_layer = mask_layer-mask_data
     mask_layer = image_background*mask_layer
     image_add = img_multi+mask_layer
     image_add = image_add*255
     image_add = image_add.astype(np.uint8)
     # frame计数
     self.index += 1
     print("linknet_post " + str(self.index))
     # 将业务处理返回的结果数据转换为Buffer
     add_buffer = modelbox.Buffer(self.get_bind_device(), image_add)
     # 设置输出Buffer的Meta信息，此处直接拷贝输入Buffer的Meta信息
     add_buffer.copy_meta(buffer_image)
     # 将输出Buffer放入输出BufferList中
     out_image.push_back(add_buffer)
     return modelbox.Status.StatusCode.STATUS_SUCCESS
     def close(self):
     # Close the flowunit
     return modelbox.Status()
     def data_pre(self, data_context):
     # Before streaming data starts
     return modelbox.Status()
     def data_post(self, data_context):
     # After streaming data ends
     return modelbox.Status()
     def data_group_pre(self, data_context):
     # Before all streaming data starts
     return modelbox.Status()
     def data_group_post(self, data_context):
     # After all streaming data ends
     return modelbox.Status()

![9e1736414b1251b7df34aa21c912c574.gif][]

#### 搭建流程图 ####

修改virtual\_background.toml内容：

![f84762e7de433151503c5452abd4d36d.gif][]

# Copyright (C) 2020 Huawei Technologies Co., Ltd. All rights reserved.
    [driver]
    dir = ["${HILENS_APP_ROOT}/etc/flowunit",
    "${HILENS_APP_ROOT}/etc/flowunit/cpp",
    "${HILENS_APP_ROOT}/model",
    "${HILENS_MB_SDK_PATH}/flowunit"]
    skip-default = true
    [profile]
    profile=true
    trace=true
    dir="${HILENS_DATA_DIR}/mb_profile"
    [graph]
    format = "graphviz"
    graphconf = """digraph virtual_background {
        node [shape=Mrecord]
     queue_size = 1
     batch_size = 1
        # 定义节点，即功能单元及其属性
        input1[type=input, flowunit=input, device=cpu, deviceid=0]
     data_source_parser[type=flowunit, flowunit=data_source_parser, device=cpu, deviceid=0]
     video_demuxer[type=flowunit, flowunit=video_demuxer, device=cpu, deviceid=0]
     video_decoder[type=flowunit, flowunit=video_decoder, device=rknpu, deviceid=0, pix_fmt="rgb"]
     image_resize[type=flowunit, flowunit=resize, device=rknpu, deviceid=0, image_width=256, image_height=256]
     linknet_infer[type=flowunit, flowunit=linknet_infer, device=rknpu, deviceid=0]
     linknet_post[type=flowunit, flowunit=linknet_post, device=cpu, deviceid=0]
     video_out[type=flowunit, flowunit=video_out, device=rknpu, deviceid=0]
        # 定义边，即功能间的数据传递关系
        input1:input -> data_source_parser:in_data
     data_source_parser:out_video_url -> video_demuxer:in_video_url
     video_demuxer:out_video_packet -> video_decoder:in_video_packet
     video_decoder:out_video_frame -> image_resize:in_image
     image_resize:out_image -> linknet_infer:Input
     linknet_infer:Output -> linknet_post:in_mask
     video_decoder:out_video_frame -> linknet_post:in_image
     linknet_post:out_image -> video_out:in_video_frame
    }"""
    [flow]
    desc = "virtual_background run in modelbox-rk-aarch64"

![39aa3e7e7991b288ac52ba0fc880307a.gif][]

其中，profile字段设为true启用性能统计功能。

#### 运行应用 ####

应用的输入和输出可以在项目工程的bin/mock\_task.toml中进行配置：

![79f7bf71b1a5cc0128b126716d378c7f.png][]

配置应用的输入输出，接下来就可以进入项目进行构建和运行了：

![ba5109304f85a5443d36089c3156b512.png][]

执行bin/main.sh运行应用，生成的视频和性能统计文件在hilens\_data\_dir文件夹：

![2d172ee71c5ec18591dd69ce27c46ad2.png][]

可以右键下载查看性能统计文件：

![8bf6cb8716f9c8ecc962d0df6efa9522.png][]

可以看到模型推理确实很快，平均每4次推理耗时223ms，fps约等于18帧每秒。

#### 开发板摄像头检测 ####

创建virtual\_background\_cameral.toml文件，编辑内容如下：

![5677c1bf0884e1570065c90d8307abc2.gif][]

# Copyright (C) 2020 Huawei Technologies Co., Ltd. All rights reserved.
    [driver]
    dir = ["${HILENS_APP_ROOT}/etc/flowunit",
    "${HILENS_APP_ROOT}/etc/flowunit/cpp",
    "${HILENS_APP_ROOT}/model",
    "${HILENS_MB_SDK_PATH}/flowunit"]
    skip-default = true
    [profile]
    profile=false
    trace=false
    dir="${HILENS_DATA_DIR}/mb_profile"
    [graph]
    format = "graphviz"
    graphconf = """digraph virtual_background {
        node [shape=Mrecord]
     queue_size = 1
     batch_size = 1
        # 定义节点，即功能单元及其属性
        input1[type=input, flowunit=input, device=cpu, deviceid=0]
     data_source_parser[type=flowunit, flowunit=data_source_parser, device=cpu, deviceid=0]
     local_camera[type=flowunit, flowunit=local_camera, device=rknpu, deviceid=0, pix_fmt="rgb", cam_width=1280, cam_height=720]
     image_resize[type=flowunit, flowunit=resize, device=rknpu, deviceid=0, image_width=256, image_height=256]
     linknet_infer[type=flowunit, flowunit=linknet_infer, device=rknpu, deviceid=0]
     linknet_post[type=flowunit, flowunit=linknet_post, device=cpu, deviceid=0]
     video_out[type=flowunit, flowunit=video_out, device=rknpu, deviceid=0]
        # 定义边，即功能间的数据传递关系
        input1:input -> data_source_parser:in_data
     data_source_parser:out_video_url -> local_camera:in_camera_packet
     local_camera:out_camera_frame -> image_resize:in_image
     image_resize:out_image -> linknet_infer:Input
     linknet_infer:Output -> linknet_post:in_mask
     local_camera:out_camera_frame -> linknet_post:in_image
     linknet_post:out_image -> video_out:in_video_frame
    }"""
    [flow]
    desc = "virtual_background run in modelbox-rk-aarch64"

![43014e3b4d5a84f5ce4e91e8b3be8de4.gif][]

打开工程目录下bin/mock\_task.toml文件，修改任务输入和任务输出：

![4cbba9f7660eab20057808017a42b1c2.png][]

执行bin/main.sh camera运行应用，使用rtsp推流到本地进行查看：

![06685fc84b86362607ea865ac217f78d.png][]

[format_png]: https://img-blog.csdnimg.cn/img_convert/0fe5aebcde1a61bea17309d510145a3a.webp?x-oss-process=image/format,png
[16dc053d314419d6135369a7715389d3.png]: https://img-blog.csdnimg.cn/img_convert/16dc053d314419d6135369a7715389d3.png
[AI_-]: https://marketplace.huaweicloud.com/contents/2b73a21b-91c5-4c58-a61a-5a5460afeaf7
[Notebook]: https://developer.huaweicloud.com/develop/aigallery/notebook/detail?id=2ef1221b-bea6-4752-961e-e52bbb85047c
[b68f7efd8e1480b714a6045e10b592d8.png]: https://img-blog.csdnimg.cn/img_convert/b68f7efd8e1480b714a6045e10b592d8.png
[Notebook 1]: https://developer.huaweicloud.com/develop/aigallery/notebook/detail?id=9d423594-4908-4a7f-beb7-f1f1a7c6c83a
[75bf5beba4268723d599b23120ba7a12.png]: https://img-blog.csdnimg.cn/img_convert/75bf5beba4268723d599b23120ba7a12.png
[9e29f3ca971417e70aac7aa14a9f777a.png]: https://img-blog.csdnimg.cn/img_convert/9e29f3ca971417e70aac7aa14a9f777a.png
[Notebook 2]: https://developer.huaweicloud.com/develop/aigallery/notebook/detail?id=11bb9328-7d85-4a6e-b148-de9deecd7f75
[4caec1f001752fb8140766f24846e12c.png]: https://img-blog.csdnimg.cn/img_convert/4caec1f001752fb8140766f24846e12c.png
[5e4432b90791b6bd9bec366e4eff87cf.png]: https://img-blog.csdnimg.cn/img_convert/5e4432b90791b6bd9bec366e4eff87cf.png
[1744b6e36287a1a4e0133074243648f7.gif]: https://img-blog.csdnimg.cn/img_convert/1744b6e36287a1a4e0133074243648f7.gif
[5f99890f4d636326c8c5d16d8d2643f3.gif]: https://img-blog.csdnimg.cn/img_convert/5f99890f4d636326c8c5d16d8d2643f3.gif
[7e3d65c17181f237882f3404f556fe3b.png]: https://img-blog.csdnimg.cn/img_convert/7e3d65c17181f237882f3404f556fe3b.png
[Link 1]: https://pan.baidu.com/s/1ZqZrrmNwNpP-WY9JgXc5NQ?pwd=65le
[aa3dfc66dd3b42bc856d2f92f27d4881.png]: https://img-blog.csdnimg.cn/img_convert/aa3dfc66dd3b42bc856d2f92f27d4881.png
[4afcf05edf902bd5c388852b0f7a80ce.png]: https://img-blog.csdnimg.cn/img_convert/4afcf05edf902bd5c388852b0f7a80ce.png
[ffa1a508e6f9cd3c593af95919b7056c.png]: https://img-blog.csdnimg.cn/img_convert/ffa1a508e6f9cd3c593af95919b7056c.png
[9c82a465a7da1372cb33fdcb4f771f9f.gif]: https://img-blog.csdnimg.cn/img_convert/9c82a465a7da1372cb33fdcb4f771f9f.gif
[e97a3bf3956fe5260de6edf622e31074.gif]: https://img-blog.csdnimg.cn/img_convert/e97a3bf3956fe5260de6edf622e31074.gif
[bd13ba30d7d12b8913b7ea93579f8f30.png]: https://img-blog.csdnimg.cn/img_convert/bd13ba30d7d12b8913b7ea93579f8f30.png
[c6a4a17508e58ac81a9f821b9abf1a2d.png]: https://img-blog.csdnimg.cn/img_convert/c6a4a17508e58ac81a9f821b9abf1a2d.png
[format_png 1]: https://img-blog.csdnimg.cn/img_convert/bb49cf93c15fe640da4cc7a36b12bc33.webp?x-oss-process=image/format,png
[00662f66f30bd053ff242085d00c5024.png]: https://img-blog.csdnimg.cn/img_convert/00662f66f30bd053ff242085d00c5024.png
[99e30018fe738d6dbda0debc1ce702f8.png]: https://img-blog.csdnimg.cn/img_convert/99e30018fe738d6dbda0debc1ce702f8.png
[82d320a4cfe1c426b2ca3746b3c7a1ca.gif]: https://img-blog.csdnimg.cn/img_convert/82d320a4cfe1c426b2ca3746b3c7a1ca.gif
[5ed7b5c35b8559f61109ead4b4bd0f73.gif]: https://img-blog.csdnimg.cn/img_convert/5ed7b5c35b8559f61109ead4b4bd0f73.gif
[eadf9e51fb602aafa87c1b62cbcce555.png]: https://img-blog.csdnimg.cn/img_convert/eadf9e51fb602aafa87c1b62cbcce555.png
[c096133a24565025ef5c9f60f2914f65.gif]: https://img-blog.csdnimg.cn/img_convert/c096133a24565025ef5c9f60f2914f65.gif
[f6ae69cec8ca638a7b77822307de002d.gif]: https://img-blog.csdnimg.cn/img_convert/f6ae69cec8ca638a7b77822307de002d.gif
[67c6563bdf7135d846a4473337849f71.gif]: https://img-blog.csdnimg.cn/img_convert/67c6563bdf7135d846a4473337849f71.gif
[9e1736414b1251b7df34aa21c912c574.gif]: https://img-blog.csdnimg.cn/img_convert/9e1736414b1251b7df34aa21c912c574.gif
[f84762e7de433151503c5452abd4d36d.gif]: https://img-blog.csdnimg.cn/img_convert/f84762e7de433151503c5452abd4d36d.gif
[39aa3e7e7991b288ac52ba0fc880307a.gif]: https://img-blog.csdnimg.cn/img_convert/39aa3e7e7991b288ac52ba0fc880307a.gif
[79f7bf71b1a5cc0128b126716d378c7f.png]: https://img-blog.csdnimg.cn/img_convert/79f7bf71b1a5cc0128b126716d378c7f.png
[ba5109304f85a5443d36089c3156b512.png]: https://img-blog.csdnimg.cn/img_convert/ba5109304f85a5443d36089c3156b512.png
[2d172ee71c5ec18591dd69ce27c46ad2.png]: https://img-blog.csdnimg.cn/img_convert/2d172ee71c5ec18591dd69ce27c46ad2.png
[8bf6cb8716f9c8ecc962d0df6efa9522.png]: https://img-blog.csdnimg.cn/img_convert/8bf6cb8716f9c8ecc962d0df6efa9522.png
[5677c1bf0884e1570065c90d8307abc2.gif]: https://img-blog.csdnimg.cn/img_convert/5677c1bf0884e1570065c90d8307abc2.gif
[43014e3b4d5a84f5ce4e91e8b3be8de4.gif]: https://img-blog.csdnimg.cn/img_convert/43014e3b4d5a84f5ce4e91e8b3be8de4.gif
[4cbba9f7660eab20057808017a42b1c2.png]: https://img-blog.csdnimg.cn/img_convert/4cbba9f7660eab20057808017a42b1c2.png
[06685fc84b86362607ea865ac217f78d.png]: https://img-blog.csdnimg.cn/img_convert/06685fc84b86362607ea865ac217f78d.png