养猪大户必备！教你用ModelBox开发一个AI数猪应用-低调大师

养猪大户必备！教你用ModelBox开发一个AI数猪应用

2024-06-20 321

本文分享自华为云社区《ModelBox-视频应用开发：AI智能数猪【玩转华为云】》，作者：阳光大猫。

一、准备环境

ModelBox端云协同AI开发套件（Windows）环境准备【ModelArts+ModelBox 端云协同AI应用开发实训课程】

二、应用开发

1. 创建工程

在ModelBox sdk目录下使用create.bat创建yolov7_pig工程：

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> .\create.bat -t server -n yolov7_pig 

(tensorflow) D:\modelbox-win10-x64-1.5.3>set BASE_PATH=D:\modelbox-win10-x64-1.5.3\ 

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PATH=D:\modelbox-win10-x64-1.5.3\\python-embed;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3\envs\tensorflow;C:\Users\yanso\miniconda3\envs\tensorflow\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\usr\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Scripts;C:\Users\yanso\miniconda3\envs\tensorflow\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\Library\usr\bin;C:\Users\yanso\miniconda3\Library\bin;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin 

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONPATH=

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONHOME=

(tensorflow) D:\modelbox-win10-x64-1.5.3>python.exe -u D:\modelbox-win10-x64-1.5.3\\create.py -t server -n yolov7_pig
sdk version is modelbox-win10-x64-1.5.3
dos2unix: converting file D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig/graph\modelbox.conf to Unix format...
dos2unix: converting file D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig/graph\yolov7_pig.toml to Unix format...
dos2unix: converting file D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig/bin\mock_task.toml to Unix format...
success: create yolov7_pig in D:\modelbox-win10-x64-1.5.3\workspace

create.bat工具的参数中，-t表示所创建实例的类型，包括server（ModelBox工程）、python（Python功能单元）、c++（C++功能单元）、infer（推理功能单元）等；-n表示所创建实例的名称，开发者自行命名。

2. 创建推理功能单元

在ModelBox sdk目录下使用create.bat创建yolov7_infer推理功能单元：

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> .\create.bat -t infer -n yolov7_infer -p yolov7_pig  

(tensorflow) D:\modelbox-win10-x64-1.5.3>set BASE_PATH=D:\modelbox-win10-x64-1.5.3\

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PATH=D:\modelbox-win10-x64-1.5.3\\python-embed;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3\envs\tensorflow;C:\Users\yanso\miniconda3\envs\tensorflow\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\usr\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Scripts;C:\Users\yanso\miniconda3\envs\tensorflow\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\Library\usr\bin;C:\Users\yanso\miniconda3\Library\bin;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONPATH=

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONHOME=

(tensorflow) D:\modelbox-win10-x64-1.5.3>python.exe -u D:\modelbox-win10-x64-1.5.3\\create.py -t infer -n yolov7_infer -p yolov7_pig
sdk version is modelbox-win10-x64-1.5.3

create.bat工具使用时，-t infer 即表示创建的是推理功能单元；-n xxx_infer 表示创建的功能单元名称为xxx_infer；-p yolov7_pig 表示所创建的功能单元属于yolov7_pig应用。

a. 下载转换好的模型

运行Notebook下载转换好的ONNX格式模型

b. 修改模型配置文件

模型和配置文件保持在同级目录下

# Copyright (C) 2020 Huawei Technologies Co., Ltd. All rights reserved.

[base]
name = "yolov7_infer"
device = "cpu"
version = "1.0.0"
description = "your description"
entry = "./best.onnx"  # model file path, use relative path
type = "inference" 
virtual_type = "onnx" # inference engine type: win10 now only support onnx
group_type = "Inference"  # flowunit group attribution, do not change

# Input ports description
[input]
[input.input1]  # input port number, Format is input.input[N]
name = "Input"  # input port name
type = "float"  # input port data type ,e.g. float or uint8
device = "cpu"  # input buffer type: cpu, win10 now copy input from cpu

# 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

3. 创建后处理功能单元

在ModelBox sdk目录下使用create.bat创建yolov7_post后处理功能单元

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> .\create.bat -t python -n yolov7_post -p yolov7_pig

(tensorflow) D:\modelbox-win10-x64-1.5.3>set BASE_PATH=D:\modelbox-win10-x64-1.5.3\ 

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PATH=D:\modelbox-win10-x64-1.5.3\\python-embed;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3\envs\tensorflow;C:\Users\yanso\miniconda3\envs\tensorflow\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\usr\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Scripts;C:\Users\yanso\miniconda3\envs\tensorflow\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\Library\usr\bin;C:\Users\yanso\miniconda3\Library\bin;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONPATH=

(tensorflow) D:\modelbox-win10-x64-1.5.3>set PYTHONHOME=

(tensorflow) D:\modelbox-win10-x64-1.5.3>python.exe -u D:\modelbox-win10-x64-1.5.3\\create.py -t python -n yolov7_post -p yolov7_pig
sdk version is modelbox-win10-x64-1.5.3
success: create python yolov7_post in D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig/etc/flowunit/yolov7_post

a. 修改配置文件

# Copyright (c) Huawei Technologies Co., Ltd. 2022. All rights reserved.

# Basic config
[base]
name = "yolov7_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 = "yolov7_post@yolov7_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]
net_h = 640
net_w = 640
num_classes = 1
conf_threshold = 0.5
iou_threshold = 0.45

# Input ports description
[input]
[input.input1] # Input port number, the format is input.input[N]
name = "in_feat" # Input port name
type = "float" # Input port type

# Output ports description
[output]
[output.output1] # Output port number, the format is output.output[N]
name = "out_data" # Output port name
type = "string" # Output port type

b. 修改逻辑代码

# 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 json
import cv2

class yolov7_postFlowUnit(modelbox.FlowUnit):
    # Derived from modelbox.FlowUnit
    def __init__(self):
        super().__init__()

    # Open the flowunit to obtain configuration information
    def open(self, config):
        # 获取功能单元的配置参数
        self.params = {}
        self.params['net_h'] = config.get_int('net_h')
        self.params['net_w'] = config.get_int('net_w')
        self.params['num_classes'] = config.get_int('num_classes')
        self.params['conf_thre'] = config.get_float('conf_threshold')
        self.params['nms_thre'] = config.get_float('iou_threshold')
        self.num_classes = config.get_int('num_classes')

        return modelbox.Status.StatusCode.STATUS_SUCCESS

    # Process the data
    def process(self, data_context):
        # 从DataContext中获取输入输出BufferList对象
        in_feat = data_context.input("in_feat")
        out_data = data_context.output("out_data")

        # yolov7_post process code.
        # 循环处理每一个输入Buffer数据
        for buffer_feat in in_feat:
            # 将输入Buffer转换为numpy对象
            feat_data = np.array(buffer_feat.as_object(), copy=False)
            feat_data = feat_data.reshape((-1, self.num_classes + 5))

            # 业务处理：解码yolov7模型的输出数据，得到检测框，转化为json数据
            bboxes = self.postprocess(feat_data, self.params)
            result = {"det_result": str(bboxes)}

            # 将业务处理返回的结果数据转换为Buffer
            result_str = json.dumps(result)
            out_buffer = modelbox.Buffer(self.get_bind_device(), result_str)

            # 将输出Buffer放入输出BufferList中
            out_data.push_back(out_buffer)

        return modelbox.Status.StatusCode.STATUS_SUCCESS
    
    # model post-processing function
    def postprocess(self, feat_data, params):
        """postprocess for yolo7 model"""
        boxes = []
        class_ids = []
        confidences = []
        for detection in feat_data:
            scores = detection[5:]
            class_id = np.argmax(scores)
            if params['num_classes'] == 1:
                confidence = detection[4]
            else:
                confidence = detection[4] * scores[class_id] 
            if confidence > params['conf_thre']:
                center_x = detection[0] / params['net_w']
                center_y = detection[1] / params['net_h']
                width = detection[2] / params['net_w']
                height = detection[3] / params['net_h']

                left = center_x - width / 2
                top = center_y - height / 2

                class_ids.append(class_id)
                confidences.append(confidence)
                boxes.append([left, top, width, height])

        # use nms algorithm in opencv
        box_idx = cv2.dnn.NMSBoxes(boxes, confidences, params['conf_thre'], params['nms_thre'])

        detections = []
        for i in box_idx:
            boxes[i][0] = max(0.0, boxes[i][0])  # [0, 1]
            boxes[i][1] = max(0.0, boxes[i][1])  # [0, 1]
            boxes[i][2] = min(1.0, boxes[i][0] + boxes[i][2])  # [0, 1]
            boxes[i][3] = min(1.0, boxes[i][1] + boxes[i][3])  # [0, 1]
            dets = np.concatenate(
                [boxes[i], np.array([confidences[i]]), np.array([class_ids[i]])], 0).tolist()
            detections.append(dets)

        return detections

    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()

4. 创建绘图功能单元

在ModelBox sdk目录下使用create.bat创建draw_pig_bbox绘图功能单元：

a. 修改配置文件

# Copyright (c) Huawei Technologies Co., Ltd. 2022. All rights reserved.

# Basic config
[base]
name = "draw_pig_bbox" # 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 = "draw_pig_bbox@draw_pig_bboxFlowUnit" # 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]
item = "value"

# Input ports description
[input]
[input.input1] # Input port number, the format is input.input[N]
name = "in_image" # Input port name
type = "uint8" # Input port type

[input.input2] # Input port number, the format is input.input[N]
name = "in_box" # Input port name
type = "string" # 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

b. 修改逻辑代码

# 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 json
import cv2

class draw_pig_bboxFlowUnit(modelbox.FlowUnit):
    # Derived from modelbox.FlowUnit
    def __init__(self):
        super().__init__()

    def open(self, config):
        # Open the flowunit to obtain configuration information
        return modelbox.Status.StatusCode.STATUS_SUCCESS

    def process(self, data_context):
        # Process the data
        in_image = data_context.input("in_image")
        in_box = data_context.input("in_box")
        out_image = data_context.output("out_image")

        # draw_image process code.
        # Remove the following code and add your own code here.
        for buffer_img, buffer_box in zip(in_image, in_box):
            width =  buffer_img.get("width")
            height = buffer_img.get("height")
            channel = buffer_img.get("channel")

            img_data = np.array(buffer_img.as_object(), copy=False)
            img_data = img_data.reshape((height, width, channel))

            bbox_str = buffer_box.as_object()
            bboxes = self.decode_car_bboxes(bbox_str, (height, width))
            img_out = self.draw_bboxes(img_data, bboxes)

            out_buffer = modelbox.Buffer(self.get_bind_device(), img_out)
            out_buffer.copy_meta(buffer_img)
            out_image.push_back(out_buffer)

        return modelbox.Status.StatusCode.STATUS_SUCCESS
    
    def decode_car_bboxes(self, bbox_str, input_shape):
        try:
            labels = [0]  # pig
            bboxes = json.loads(json.loads(bbox_str)['det_result'])
            bboxes = list(filter(lambda x: int(x[5]) in labels, bboxes))
        except Exception as ex:
            print(str(ex))
            return []
        else:
            for bbox in bboxes:
                bbox[0] = int(bbox[0] * input_shape[1])
                bbox[1] = int(bbox[1] * input_shape[0])
                bbox[2] = int(bbox[2] * input_shape[1])
                bbox[3] = int(bbox[3] * input_shape[0])
            return bboxes
        
    def draw_bboxes(self, img_data, bboxes):
        '''画框'''
        count = len(bboxes)
        cv2.putText(img_data, 'pig_count: '+str(count), (20, 40), cv2.FONT_HERSHEY_TRIPLEX, 1.5, (255, 0, 0), thickness=2)
        for bbox in bboxes:
            x1, y1, x2, y2, score, label = bbox
            color = (0, 0, 255)
            names = ['pig']  
            score = '%.2f' % score
            label = '%s:%s' % (names[int(label)], score)
            cv2.rectangle(img_data, (x1, y1), (x2, y2), color, 2)
            cv2.putText(img_data, label, (x1, y1 - 10), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (0, 255, 0), thickness=1)
        return img_data

    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()

5. 修改流程图

yolov7_pig工程graph目录下存放流程图，默认的流程图yolov7_pig.toml与工程同名，其内容为（以Windows版ModelBox为例）：

# 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 yolov7_pig {
    node [shape=Mrecord]
    queue_size = 4
    batch_size = 1
    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=cpu, deviceid=0, pix_fmt=rgb]
    image_resize[type=flowunit, flowunit=resize, device=cpu, deviceid=0, image_width=640, image_height=640]
    image_transpose[type=flowunit, flowunit=packed_planar_transpose, device=cpu, deviceid=0]
    normalize[type=flowunit flowunit=normalize device=cpu deviceid=0 standard_deviation_inverse="0.0039215686,0.0039215686,0.0039215686"]
    yolov7_infer[type=flowunit, flowunit=yolov7_infer, device=cpu, deviceid=0, batch_size = 1]
    yolov7_post[type=flowunit, flowunit=yolov7_post, device=cpu, deviceid=0]
    draw_pig_bbox[type=flowunit, flowunit=draw_pig_bbox, device=cpu, deviceid=0]
    video_out[type=flowunit, flowunit=video_out, device=cpu, deviceid=0]
    
    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 -> image_transpose:in_image
    image_transpose:out_image -> normalize:in_data
    normalize:out_data -> yolov7_infer:Input
    yolov7_infer:Output -> yolov7_post:in_feat
    video_decoder:out_video_frame -> draw_pig_bbox:in_image
    yolov7_post:out_data -> draw_pig_bbox:in_box
    draw_pig_bbox:out_image -> video_out:in_video_frame
}"""
[flow]
desc = "yolov7_pig run in modelbox-win10-x64"

yolov7_pig工程graph目录下存放流程图，新建流程图yolov7_pig_http.toml，其内容为（以Windows版ModelBox为例）：

# 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 yolov7_pig {
    node [shape=Mrecord]
    queue_size = 4
    batch_size = 1
    input1[type=input,flowunit=input,device=cpu,deviceid=0]

    httpserver_sync_receive[type=flowunit, flowunit=httpserver_sync_receive_v2, device=cpu, deviceid=0, time_out_ms=5000, endpoint="http://0.0.0.0:8083/v1/yolov7_pig", max_requests=100]
    image_decoder[type=flowunit, flowunit=image_decoder, device=cpu, key="image_base64", queue_size=4]
    image_resize[type=flowunit, flowunit=resize, device=cpu, deviceid=0, image_width=640, image_height=640]
    image_transpose[type=flowunit, flowunit=packed_planar_transpose, device=cpu, deviceid=0]
    normalize[type=flowunit flowunit=normalize device=cpu deviceid=0 standard_deviation_inverse="0.0039215686,0.0039215686,0.0039215686"]
    yolov7_infer[type=flowunit, flowunit=yolov7_infer, device=cpu, deviceid=0, batch_size = 1]
    yolov7_post[type=flowunit, flowunit=yolov7_post, device=cpu, deviceid=0]
    httpserver_sync_reply[type=flowunit, flowunit=httpserver_sync_reply_v2, device=cpu, deviceid=0]
    
    input1:input -> httpserver_sync_receive:in_url
    httpserver_sync_receive:out_request_info -> image_decoder:in_encoded_image
    image_decoder:out_image -> image_resize:in_image
    image_resize:out_image -> image_transpose:in_image
    image_transpose:out_image -> normalize:in_data
    normalize:out_data -> yolov7_infer:Input
    yolov7_infer:Output -> yolov7_post:in_feat
    yolov7_post:out_data -> httpserver_sync_reply:in_reply_info
}"""
[flow]
desc = "yolov7_pig run in modelbox-win10-x64"

三、运行应用

准备测试视频和测试图片，在yolov7_pet工程目录下修改bin/mock_task.toml配置文件：

# 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${HILENS_APP_ROOT}所在目录文件输入)
# 4. http服务：type="url", url="http://xxx.xxx"(指的是任务作为http服务启动，此处需填写对外暴露的http服务地址，需配合httpserver类的功能单元使用)
# 5. 支持多输入[input] [input1] [input2] ...，对应的输出为[output] [output1] [output2] ...，如果使用videoout功能单元输出，则输入和输出个数必须匹配，同时url不能重名
[input]
type = "url"
url = "${HILENS_APP_ROOT}/data/pig.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${HILENS_DATA_DIR}所在目录或子目录)
# 4. http服务：type="webhook", url="http://xxx.xxx" (指的是任务产生的数据上报给某个http服务，此处需填写上传的http服务地址)
[output]
type = "local"
# url = "0:pig_det"  
url = "${HILENS_APP_ROOT}/hilens_data_dir/pig_detection_result.mp4"

在yolov7_pig工程目录下执行.\bin\main.bat运行应用：

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> cd D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig
(tensorflow) PS D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig> .\bin\main.bat     

(tensorflow) D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig>set PATH=D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../../../python-embed;D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../../../modelbox-win10-x64/bin;D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../dependence/lib;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3\envs\tensorflow;C:\Users\yanso\miniconda3\envs\tensorflow\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\usr\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Scripts;C:\Users\yanso\miniconda3\envs\tensorflow\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\Library\usr\bin;C:\Users\yanso\miniconda3\Library\bin;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin

(tensorflow) D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig>modelbox.exe -c D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../graph/modelbox.conf
[2024-06-18 19:16:51,441][ WARN][    iva_config.cc:143 ] update vas url failed. Fault, no vas projectid or iva endpoint
open log file D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../hilens_data_dir/log/modelbox.log failed, No error
input dims is:1,3,640,640,
output dims is:1,25200,6,
[h264_mf @ 0000000046bab040] MFT name: 'H264 Encoder MFT'
[2024-06-18 19:17:44,535][ WARN][ffmpeg_video_muxer.cc:78  ] Success: video stream has been written to D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/hilens_data_dir/pig_detection_result.mp4
[2024-06-18 19:17:44,788][ERROR][flow_scheduler.cc:438 ] the scheduler caught an error : Stop operation
Press any key to continue . . .

生成的视频保存在yolov7_pig工程目录下hilens_data_dir文件夹中：

在yolov7_pig工程目录下执行.\bin\main.bat http开启HTTP服务：

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> cd D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig                                                                             
(tensorflow) PS D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig> .\bin\main.bat http

(tensorflow) D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig>set PATH=D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../../../python-embed;D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../../../modelbox-win10-x64/bin;D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../dependence/lib;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3\envs\tensorflow;C:\Users\yanso\miniconda3\envs\tensorflow\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\usr\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Library\bin;C:\Users\yanso\miniconda3\envs\tensorflow\Scripts;C:\Users\yanso\miniconda3\envs\tensorflow\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\yanso\miniconda3\envs\tensorflow\lib\site-packages\pywin32_system32;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Library\mingw-w64\bin;C:\Users\yanso\miniconda3\Library\usr\bin;C:\Users\yanso\miniconda3\Library\bin;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\bin;C:\Users\yanso\miniconda3\condabin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin;C:\Windows\System32\HWAudioDriverLibs;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0;C:\Windows\System32\OpenSSH;C:\Users\Administrator\AppData\Local\Microsoft\WindowsApps;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0;C:\WINDOWS\System32\OpenSSH;C:\Program Files\Git\cmd;C:\Users\yanso\miniconda3;C:\Users\yanso\miniconda3\Scripts;C:\Users\yanso\miniconda3\Library\bin;.;C:\Program Files\Git LFS;C:\Users\yanso\AppData\Local\Microsoft\WindowsApps;.;C:\Users\yanso\AppData\Local\Programs\Microsoft VS Code\bin

(tensorflow) D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig>modelbox.exe -c D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../graph/modelbox.conf
[2024-06-18 19:23:53,655][ WARN][    iva_config.cc:143 ] update vas url failed. Fault, no vas projectid or iva endpoint
open log file D:/modelbox-win10-x64-1.5.3/workspace/yolov7_pig/bin/../hilens_data_dir/log/modelbox.log failed, No error
input dims is:1,3,640,640,
output dims is:1,25200,6,

HTTP服务启动后可以在另一个终端进行请求测试，进入yolov7_pig工程目录data文件夹中创建test_http.py脚本然后发起HTTP请求进行测试：

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Copyright (c) Huawei Technologies Co., Ltd. 2022. All rights reserved.

import os
import cv2
import json
import base64
import http.client
class HttpConfig:
    '''http调用的参数配置'''
    def __init__(self, host_ip, port, url, img_base64_str):
        self.hostIP = host_ip
        self.Port = port

        self.httpMethod = "POST"
        self.requstURL = url
        self.headerdata = {
            "Content-Type": "application/json"
        }
        self.test_data = {
            "image_base64": img_base64_str
        }
        self.body = json.dumps(self.test_data)
def read_image(img_path):
    '''读取图片数据并转为base64编码的字符串'''
    img_data = cv2.imread(img_path)
    img_str = cv2.imencode('.jpg', img_data)[1].tostring()
    img_bin = base64.b64encode(img_str)
    img_base64_str = str(img_bin, encoding='utf8')

    return img_data, img_base64_str
def decode_car_bboxes(bbox_str, input_shape):
    try:
        labels = [0, 1]  # cat, dog
        bboxes = json.loads(json.loads(bbox_str)['det_result'])
        bboxes = list(filter(lambda x: int(x[5]) in labels, bboxes))
    except Exception as ex:
        print(str(ex))
        return []
    else:
        for bbox in bboxes:
            bbox[0] = int(bbox[0] * input_shape[1])
            bbox[1] = int(bbox[1] * input_shape[0])
            bbox[2] = int(bbox[2] * input_shape[1])
            bbox[3] = int(bbox[3] * input_shape[0])

        return bboxes
def draw_bboxes(img_data, bboxes):
    '''绘制检测框'''
    count = len(bboxes)
    cv2.putText(img_data, 'pig_count: '+str(count), (20, 40), cv2.FONT_HERSHEY_TRIPLEX, 1.5, (255, 0, 0), thickness=2)
    for bbox in bboxes:
        x1, y1, x2, y2, score, label = bbox
        color = (0, 0, 255)
        names = ['pig']  
        score = '%.2f' % score
        label = '%s:%s' % (names[int(label)], score)
        cv2.rectangle(img_data, (x1, y1), (x2, y2), color, 2)
        cv2.putText(img_data, label, (x1, y1 - 10), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (0, 255, 0), thickness=1)

    return img_data, count
def test_image(img_path, ip, port, url):
    '''单张图片测试'''
    img_data, img_base64_str = read_image(img_path)
    http_config = HttpConfig(ip, port, url, img_base64_str)

    conn = http.client.HTTPConnection(host=http_config.hostIP, port=http_config.Port)
    conn.request(method=http_config.httpMethod, url=http_config.requstURL,
                body=http_config.body, headers=http_config.headerdata)

    response = conn.getresponse().read().decode()
    print('response: ', response)

    bboxes = decode_car_bboxes(response, img_data.shape)
    imt_out, count = draw_bboxes(img_data, bboxes)
    cv2.imwrite('./result-' + os.path.basename(img_path), imt_out)

    return count
if __name__ == "__main__":
    port = 8083
    ip = "127.0.0.1"
    url = "/v1/yolov7_pig"
    img_folder = './test_imgs'
    file_list = os.listdir(img_folder)
    for img_file in file_list:
        print("\n================ {} ================".format(img_file))
        img_path = os.path.join(img_folder, img_file)
        count = test_image(img_path, ip, port, url)
        print("================ pig_count: {} ================".format(count))

(tensorflow) PS D:\modelbox-win10-x64-1.5.3> cd D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig\data
(tensorflow) PS D:\modelbox-win10-x64-1.5.3\workspace\yolov7_pig\data> D:\modelbox-win10-x64-1.5.3\python-embed\python.exe .\test_http.py

================ 20190515142012.jpg ================
.\test_http.py:33: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  img_str = cv2.imencode('.jpg', img_data)[1].tostring()
response:  {"det_result": "[[0.5314995586872101, 0.41453492641448975, 0.6529222667217255, 0.6227057695388794, 0.9563100934028625, 0.0], [0.5491283953189849, 0.6111114203929902, 0.6829706609249114, 0.7607279121875763, 0.9505243301391602, 0.0], [0.7092265635728836, 0.32529172897338865, 0.7929001301527023, 0.5090352058410644, 0.9247245192527771, 0.0], [0.7478243410587311, 0.24942492246627807, 0.8540475308895111, 0.3306758046150208, 0.8886529207229614, 0.0], [0.2863448441028595, 0.7783691227436066, 0.40429784655570983, 0.9388670146465301, 0.8832182288169861, 0.0], [0.3198540091514588, 0.7068635761737824, 0.469990885257721, 0.8155526340007783, 0.8750752806663513, 0.0], [0.8573761910200118, 0.1112288475036621, 0.9163458853960037, 0.24985072612762452, 0.8558010458946228, 0.0], [0.19583110213279725, 0.4393650829792023, 0.3086510717868805, 0.5697859942913055, 0.8494003415107727, 0.0], [0.6343106091022491, 0.031079763174057015, 0.7757764041423798, 0.11533512473106385, 0.8335027098655701, 0.0], [0.32979671955108647, 0.24954813718795776, 0.41185748577117925, 0.4911258816719055, 0.8318935036659241, 0.0], [0.42157947421073916, 0.6686352252960205, 0.5486672222614288, 0.8406521320343017, 0.8014721274375916, 0.0], [0.036364993453025816, 0.3792011857032776, 0.11506653130054473, 0.5173661589622498, 0.7864469289779663, 0.0], [0.18477005362510682, 0.7536652505397796, 0.2830569803714752, 0.9396657049655914, 0.7493076324462891, 0.0], [0.7877487927675247, 0.0820700079202652, 0.8679187029600144, 0.16506505906581878, 0.7153295278549194, 0.0], [0.8873884886503219, 0.4463221430778504, 0.968685844540596, 0.6051429867744447, 0.6919704675674438, 0.0], [0.08014355301856996, 0.73122136592865, 0.14829849600791933, 0.8797563791275025, 0.6634459495544434, 0.0], [0.2530277907848358, 0.7759395956993104, 0.31589220166206355, 0.9465934395790101, 0.6256685853004456, 0.0], [0.059241372346878055, 0.7150145590305328, 0.1196309506893158, 0.8592026650905609, 0.6242099404335022, 0.0], [0.5020054757595062, 0.7558817148208619, 0.6267922461032867, 0.9292884588241578, 0.6164543032646179, 0.0], [0.12215411663055419, 0.6416930139064789, 0.2372045278549194, 0.7511061728000641, 0.5967950224876404, 0.0], [0.5455536484718323, 0.7130935192108154, 0.6122338652610779, 0.8517275333404541, 0.5695550441741943, 0.0]]"}
================ pig_count: 21 ================

================ 20190515142128.jpg ================
response:  {"det_result": "[[0.2530054211616516, 0.3259969651699066, 0.37694138288497925, 0.5073411047458649, 0.9552642107009888, 0.0], [0.7655192792415619, 0.37133423089981077, 0.8948265612125397, 0.5411525130271911, 0.946380078792572, 0.0], [0.7068361639976501, 0.6438457131385803, 0.8532623887062073, 0.7564051985740662, 0.9442737698554993, 0.0], [0.4689387619495392, 0.6953599870204925, 0.6093841254711152, 0.8904086172580719, 0.9394132494926453, 0.0], [0.5610995948314667, 0.41046096086502076, 0.7043379127979279, 0.5980172038078309, 0.9185187816619873, 0.0], [0.1679925262928009, 0.7986599743366241, 0.27840816378593447, 0.9098593890666961, 0.9116157293319702, 0.0], [0.6167296946048737, 0.47176125049591067, 0.7882755696773529, 0.5939736127853393, 0.9113425016403198, 0.0], [0.8483672857284545, 0.558952933549881, 0.9509815454483032, 0.6832078635692597, 0.9013326168060303, 0.0], [0.6976672232151032, 0.05890357494354248, 0.7643234193325044, 0.14790127277374268, 0.8907486200332642, 0.0], [0.3439214825630188, 0.764359337091446, 0.48462504148483276, 0.9410788953304292, 0.8897976875305176, 0.0], [0.9087600618600845, 0.41939428448677063, 0.9657777875661849, 0.5442929446697236, 0.8668227791786194, 0.0], [0.5307900249958039, 0.013786908984184262, 0.6927152812480927, 0.10742981731891632, 0.8617266416549683, 0.0], [0.06923194527626038, 0.2071500480175018, 0.1422653615474701, 0.354218989610672, 0.8515089154243469, 0.0], [0.46218110322952266, 0.543884563446045, 0.5642802119255066, 0.7718154907226563, 0.8315367102622986, 0.0], [0.12014133036136627, 0.7533746421337127, 0.20710271298885347, 0.8859859764575958, 0.8161348700523376, 0.0], [0.6099689096212387, 0.6311885595321655, 0.6959998518228531, 0.8344843149185179, 0.8158949613571167, 0.0], [0.47475093603134155, 0.15836940407752992, 0.5509012818336487, 0.3299554765224457, 0.7964221239089966, 0.0], [0.7360249996185303, 0.20219690799713136, 0.8462663173675538, 0.2739208459854126, 0.7939417958259583, 0.0], [0.8505313932895661, 0.15010038614273072, 0.905955308675766, 0.22253469228744507, 0.766402542591095, 0.0], [0.8721131294965744, 0.3546452701091766, 0.9455597907304764, 0.4159835159778595, 0.7579628825187683, 0.0], [0.8202457576990128, 0.07152213156223297, 0.8842441409826278, 0.16832662522792816, 0.7537699937820435, 0.0], [0.4672187626361847, 0.8035521984100341, 0.6121010005474091, 0.9495066165924071, 0.7330396771430969, 0.0], [0.7931241631507874, 0.07484636306762696, 0.8552763342857361, 0.2041161298751831, 0.7252987623214722, 0.0], [0.05245172083377838, 0.34656997919082644, 0.11882493197917937, 0.4487423300743103, 0.711035966873169, 0.0], [0.039842239022254936, 0.6570722877979278, 0.10100120007991789, 0.7980956733226776, 0.7003825902938843, 0.0], [0.07937039136886598, 0.6993482947349549, 0.14970344305038452, 0.808335554599762, 0.6464911699295044, 0.0], [0.0408034861087799, 0.24992489218711852, 0.08359875082969664, 0.36381874680519105, 0.6194641590118408, 0.0]]"}
================ pig_count: 27 ================

================ 20190515143224.jpg ================
response:  {"det_result": "[[0.33151587247848513, 0.7472196042537689, 0.4520726799964905, 0.944657951593399, 0.9549262523651123, 0.0], [0.6966262102127075, 0.38143407106399535, 0.8187609434127808, 0.5275840640068055, 0.9383824467658997, 0.0], [0.3309335768222809, 0.38504688739776616, 0.5029547631740571, 0.5163029432296753, 0.9308131337165833, 0.0], [0.22159602940082548, 0.2502309620380402, 0.2970270365476608, 0.4074728190898895, 0.9295130372047424, 0.0], [0.52587131857872, 0.6116060733795166, 0.6969760477542877, 0.7392594814300537, 0.9274167418479919, 0.0], [0.8019156157970428, 0.5839392662048339, 0.9134944260120392, 0.6862605094909667, 0.9207823276519775, 0.0], [0.22548656463623046, 0.7824307978153229, 0.3473879337310791, 0.9226225316524506, 0.9075026512145996, 0.0], [0.7616031408309937, 0.23449447751045227, 0.8773191690444947, 0.30470640063285825, 0.8723774552345276, 0.0], [0.47462679147720344, 0.7428544700145722, 0.659464204311371, 0.8985731422901153, 0.8692379593849182, 0.0], [0.7726404637098313, 0.047815185785293576, 0.8582356959581375, 0.16538638472557066, 0.857752799987793, 0.0], [0.04095276296138763, 0.35726237297058105, 0.09002236425876617, 0.4370449066162109, 0.8512980937957764, 0.0], [0.5121502339839935, 0.16153932213783262, 0.5878590166568756, 0.35389813780784607, 0.8481522798538208, 0.0], [0.6813990414142609, 0.5552682638168336, 0.8241379916667939, 0.7315007448196412, 0.8349569439888, 0.0], [0.7848798453807831, 0.2997883439064026, 0.8487448036670685, 0.4219695448875427, 0.8328686952590942, 0.0], [0.675277727842331, 0.5038471221923828, 0.788842660188675, 0.5971584320068359, 0.8305914998054504, 0.0], [0.36567584276199344, 0.1846299886703491, 0.4232009768486023, 0.32693817615509035, 0.8237928748130798, 0.0], [0.8332049459218979, 0.15594483613967897, 0.9077650934457778, 0.21918100118637085, 0.8095088005065918, 0.0], [0.8188231199979782, 0.5099769771099091, 0.9065980225801468, 0.5991565525531769, 0.789814293384552, 0.0], [0.16333829164505004, 0.7263919234275817, 0.23472834825515745, 0.8557828545570373, 0.77839595079422, 0.0], [0.09923059344291688, 0.5434492200613021, 0.2318732798099518, 0.6342397600412368, 0.7709190249443054, 0.0], [0.04113772809505463, 0.6769565641880035, 0.09518382847309112, 0.7874909341335297, 0.7675528526306152, 0.0], [0.12286571264266968, 0.7784929722547531, 0.18941720724105837, 0.8611520320177078, 0.7538224458694458, 0.0], [0.8486063361167908, 0.1046980857849121, 0.8987706780433655, 0.17449078559875486, 0.6860058307647705, 0.0], [0.8597557455301285, 0.3714954495429993, 0.9395408242940902, 0.5046039462089539, 0.6594332456588745, 0.0], [0.725972306728363, 0.2879889786243439, 0.8093014359474182, 0.4364859759807587, 0.6504802703857422, 0.0], [0.80337233543396, 0.43979210257530216, 0.9095016956329346, 0.5416744768619538, 0.5330303907394409, 0.0], [0.0, 0.44415642619132994, 0.03889097571372986, 0.5607487976551055, 0.5000762939453125, 0.0]]"}
================ pig_count: 27 ================

================ 20190515143432.jpg ================
response:  {"det_result": "[[0.6373811900615692, 0.4556077837944031, 0.7505947887897492, 0.6163338780403137, 0.958651065826416, 0.0], [0.7536835551261902, 0.19262979030609134, 0.853804886341095, 0.3675990819931031, 0.9556296467781067, 0.0], [0.24914194345474241, 0.1605188548564911, 0.37957080602645876, 0.2712996304035187, 0.9410728812217712, 0.0], [0.5784417808055878, 0.6893238723278046, 0.7007974922657013, 0.8144921600818634, 0.9311926364898682, 0.0], [0.4877449214458466, 0.838113933801651, 0.6275949299335479, 0.9414070546627045, 0.9248373508453369, 0.0], [0.7326700747013092, 0.5087914645671845, 0.8424749791622161, 0.6524371922016144, 0.9235878586769104, 0.0], [0.6557062178850174, 0.04749650359153747, 0.7422844856977463, 0.22362623810768129, 0.8662278056144714, 0.0], [0.7520786702632904, 0.37903311252593996, 0.8365497171878815, 0.5275002241134643, 0.8632115721702576, 0.0], [0.4560465335845947, 0.7834814339876175, 0.5788590908050537, 0.875244876742363, 0.8591019511222839, 0.0], [0.8486663192510605, 0.24308437108993527, 0.9209946304559707, 0.38057256937026973, 0.8481018543243408, 0.0], [0.06989501118659974, 0.21171223521232607, 0.14719852805137634, 0.2901284992694855, 0.8403106927871704, 0.0], [0.07931529581546784, 0.7274754464626313, 0.14586327970027924, 0.8284106314182282, 0.8276875019073486, 0.0], [0.8199215471744538, 0.5190264046192169, 0.916180557012558, 0.601987999677658, 0.8218949437141418, 0.0], [0.7753406018018723, 0.6247795641422271, 0.869887974858284, 0.7028177678585052, 0.8103967905044556, 0.0], [0.5350410103797912, 0.2904348909854889, 0.7034945845603943, 0.47202824950218203, 0.7742581367492676, 0.0], [0.7052563428878784, 0.594559383392334, 0.7930361032485962, 0.802627182006836, 0.7661027312278748, 0.0], [0.2078638195991516, 0.836474758386612, 0.3327731490135193, 0.9146723210811616, 0.7656165361404419, 0.0], [0.35651546716690063, 0.8356708973646164, 0.48673042058944704, 0.9123004466295243, 0.7651214599609375, 0.0], [0.04286686778068543, 0.651385509967804, 0.1189558446407318, 0.7819379687309265, 0.7318003177642822, 0.0], [0.16353363096714021, 0.7001014947891235, 0.23111434876918796, 0.8483508825302124, 0.7219746112823486, 0.0], [0.8943167269229888, 0.465467381477356, 0.9480641782283782, 0.5696653127670288, 0.7132480144500732, 0.0], [0.13475828468799592, 0.7123962700366974, 0.19173202216625213, 0.8635941207408905, 0.6760420203208923, 0.0], [0.9031854838132858, 0.37944490909576417, 0.9443069249391556, 0.4960151433944702, 0.6697810292243958, 0.0], [0.7169572085142135, 0.051375272870063785, 0.7699337750673294, 0.11804214417934418, 0.5670255422592163, 0.0]]"}
================ pig_count: 24 ================

================ 20190621141141.jpg ================
response:  {"det_result": "[[0.2858048617839813, 0.6920524835586548, 0.40033505558967586, 0.876273512840271, 0.9693846702575684, 0.0], [0.8160727888345719, 0.3245592772960663, 0.9153503984212876, 0.44209216237068183, 0.9652171730995178, 0.0], [0.3276993572711945, 0.2825296759605408, 0.48299114108085633, 0.4778394341468811, 0.9459359049797058, 0.0], [0.7524076730012894, 0.6082898855209351, 0.8520412176847458, 0.7410279512405396, 0.9435095191001892, 0.0], [0.52833012342453, 0.6118248403072357, 0.7453569531440735, 0.7360025942325592, 0.9292019009590149, 0.0], [0.7283130764961242, 0.24003291130065915, 0.8490503191947937, 0.41690392494201656, 0.9274832010269165, 0.0], [0.5753984153270721, 0.7113316237926484, 0.7098467171192169, 0.8695607483386993, 0.9142341613769531, 0.0], [0.3426991164684296, 0.160414856672287, 0.502489310503006, 0.24934423565864564, 0.8892913460731506, 0.0], [0.21955735087394712, 0.14540990591049194, 0.34493497014045715, 0.25439044237136843, 0.8848840594291687, 0.0], [0.17622598409652712, 0.7975501120090485, 0.28576570749282837, 0.894774717092514, 0.8471149206161499, 0.0], [0.4498146414756775, 0.7951198756694794, 0.602517569065094, 0.8975848972797394, 0.8465115427970886, 0.0], [0.336152708530426, 0.7672465980052948, 0.4467101454734802, 0.9145124733448029, 0.8383660912513733, 0.0], [0.8808505088090897, 0.5050277709960938, 0.9662985771894455, 0.6021172523498535, 0.8287425637245178, 0.0], [0.5983243703842164, 0.05242392122745514, 0.7141552209854126, 0.10514067113399506, 0.8067843317985535, 0.0], [0.03119544088840484, 0.5027143061161041, 0.09562594592571258, 0.6602520406246185, 0.8055742383003235, 0.0], [0.3866620540618897, 0.8470147281885146, 0.5265138149261475, 0.9368914455175399, 0.8049367666244507, 0.0], [0.8214336901903153, 0.2318374812602997, 0.8985568493604661, 0.337394791841507, 0.7954773902893066, 0.0], [0.6170122742652893, 0.07954724133014679, 0.7388171553611755, 0.14763021171092988, 0.7868005633354187, 0.0], [0.7230192244052887, 0.07258228063583373, 0.8153064668178558, 0.15148414373397828, 0.7648471593856812, 0.0], [0.050417631864547736, 0.6464603543281555, 0.11656169295310975, 0.7629135966300964, 0.7563851475715637, 0.0], [0.8766493797302246, 0.25733983516693115, 0.929527759552002, 0.373953652381897, 0.731341540813446, 0.0], [0.8231545478105545, 0.10986250042915345, 0.8790049523115159, 0.19118310809135436, 0.7140998840332031, 0.0], [0.10614479780197145, 0.7547796964645386, 0.18728572130203247, 0.8611701250076294, 0.6874741911888123, 0.0], [0.9011492043733597, 0.40590643882751465, 0.9454408377408982, 0.5230727672576905, 0.6780690550804138, 0.0], [0.0784837692975998, 0.7619574457406998, 0.13632536232471468, 0.8540185064077378, 0.602765679359436, 0.0]]"}
================ pig_count: 25 ================

================ 20190621141249.jpg ================
response:  {"det_result": "[[0.32586483359336854, 0.24259638190269472, 0.44065051674842837, 0.4332111418247223, 0.9233660697937012, 0.0], [0.7415802776813507, 0.20339409708976744, 0.8526828944683075, 0.3355763256549835, 0.9134587645530701, 0.0], [0.5598558843135834, 0.06444359421730042, 0.6583136141300201, 0.2255875051021576, 0.9114824533462524, 0.0], [0.25549439787864686, 0.3045780062675476, 0.3439884722232819, 0.5094657063484191, 0.8858470916748047, 0.0], [0.13424646258354186, 0.4089730978012085, 0.25759304165840147, 0.6323755502700805, 0.8812260031700134, 0.0], [0.8928446710109711, 0.36205734610557555, 0.9444068014621735, 0.5137213289737701, 0.8466163277626038, 0.0], [0.23145273327827454, 0.6901010632514953, 0.3217297732830048, 0.8946843981742858, 0.8444425463676453, 0.0], [0.8465079367160797, 0.11456479430198671, 0.89749955534935, 0.22315168976783756, 0.8440980911254883, 0.0], [0.6389145582914353, 0.08545876145362855, 0.7304814606904984, 0.15657412409782412, 0.8438040614128113, 0.0], [0.8596288859844208, 0.2315908432006836, 0.9259816944599152, 0.37012472152709963, 0.8362818956375122, 0.0], [0.3882917046546936, 0.8376923948526382, 0.524693238735199, 0.9266737550497055, 0.8342019319534302, 0.0], [0.6816271901130677, 0.6371851027011872, 0.7663943171501161, 0.8309317529201509, 0.8334851264953613, 0.0], [0.3005506873130798, 0.6813186645507812, 0.3791545510292053, 0.8741531372070311, 0.8274812698364258, 0.0], [0.33739756345748906, 0.33437139391899107, 0.5387834668159486, 0.5037173092365265, 0.8089301586151123, 0.0], [0.8224694639444351, 0.579327318072319, 0.9104406923055649, 0.6655360966920852, 0.8041741847991943, 0.0], [0.6123552083969116, 0.05221189558506012, 0.7181327104568481, 0.11119897067546844, 0.7695637345314026, 0.0], [0.8055596232414245, 0.09786717295646667, 0.8591267704963683, 0.20656116604804992, 0.7643899917602539, 0.0], [0.424746036529541, 0.10845542550086976, 0.5769085884094238, 0.19416474699974062, 0.7628222107887268, 0.0], [0.10420677959918975, 0.7469959199428557, 0.19218709170818327, 0.8613018095493316, 0.7571574449539185, 0.0], [0.17412686347961426, 0.40185985565185545, 0.27423748970031736, 0.5151351928710938, 0.7561619877815247, 0.0], [0.05058914422988891, 0.6416772782802582, 0.1131001591682434, 0.7677843153476716, 0.7416978478431702, 0.0], [0.3409019768238068, 0.7796604573726654, 0.4453953921794892, 0.9214360773563386, 0.7141085863113403, 0.0], [0.18340975642204282, 0.7990216165781021, 0.27464697957038875, 0.8974507421255111, 0.6413347125053406, 0.0], [0.04150465726852417, 0.49037010669708253, 0.08957942724227905, 0.6455666303634644, 0.546801745891571, 0.0]]"}
================ pig_count: 24 ================

================ 20190621141252.jpg ================
response:  {"det_result": "[[0.33483492136001586, 0.24801833033561704, 0.46570180654525756, 0.42209818959236145, 0.9716753363609314, 0.0], [0.2519586384296417, 0.36687822341918946, 0.3474899470806122, 0.5718529701232911, 0.9303265810012817, 0.0], [0.4155482828617096, 0.8238115727901458, 0.533502334356308, 0.9323083460330963, 0.9205400347709656, 0.0], [0.3207600831985473, 0.3376201748847961, 0.5225308179855346, 0.515419566631317, 0.8988451361656189, 0.0], [0.554785406589508, 0.05943803191184999, 0.6596805930137634, 0.22677205204963685, 0.8893870711326599, 0.0], [0.46912367045879366, 0.06897258758544922, 0.5670793324708939, 0.2043828248977661, 0.8699984550476074, 0.0], [0.8252426624298096, 0.4277828633785247, 0.9124511241912842, 0.5882897913455962, 0.8698359131813049, 0.0], [0.6787687718868256, 0.6382624804973602, 0.7658585131168366, 0.8285960018634796, 0.8679203391075134, 0.0], [0.7809970557689666, 0.18303799629211426, 0.8583998024463653, 0.3013877868652344, 0.862260639667511, 0.0], [0.2980193674564362, 0.6860662639141083, 0.3834327161312104, 0.8751100361347199, 0.8417824506759644, 0.0], [0.821492999792099, 0.5867913573980331, 0.9123088419437408, 0.6672211319208144, 0.8390227556228638, 0.0], [0.6389112740755082, 0.0899557739496231, 0.7319891661405564, 0.15791340768337248, 0.8321851491928101, 0.0], [0.33291764855384826, 0.8251787841320037, 0.4365656316280365, 0.954769641160965, 0.8283060789108276, 0.0], [0.8935729414224625, 0.35864530801773076, 0.9461084932088852, 0.5104689955711366, 0.8208484053611755, 0.0], [0.050797092914581295, 0.6406578123569489, 0.11242005825042725, 0.7678249299526214, 0.8082728385925293, 0.0], [0.08978922665119171, 0.7454609930515289, 0.18675152957439423, 0.8624686181545257, 0.8028767704963684, 0.0], [0.23195808827877046, 0.6860327363014221, 0.31602269709110264, 0.8831139922142028, 0.7864329218864441, 0.0], [0.8766951024532319, 0.23855491876602175, 0.9269677698612214, 0.36291831731796265, 0.7816985249519348, 0.0], [0.6164859116077424, 0.051790457963943486, 0.7212261855602264, 0.110322505235672, 0.7430948615074158, 0.0], [0.8110435038805008, 0.095573490858078, 0.8672638386487961, 0.21423617005348206, 0.7066771984100342, 0.0], [0.13872788548469545, 0.4524787902832031, 0.24725345969200135, 0.6506900787353516, 0.6665958762168884, 0.0], [0.8341281533241272, 0.10387264490127564, 0.8950199484825134, 0.2346912741661072, 0.6608691811561584, 0.0], [0.1852737754583359, 0.7818301141262054, 0.28252197802066803, 0.8940926611423492, 0.5649592876434326, 0.0], [0.18228755295276644, 0.38649161458015446, 0.27544007003307347, 0.5115441977977753, 0.5577556490898132, 0.0], [0.3280117630958557, 0.7540877401828766, 0.4142733454704285, 0.9178435266017915, 0.5334183573722839, 0.0]]"}
================ pig_count: 25 ================

================ 20190621141536.jpg ================
response:  {"det_result": "[[0.2564292013645172, 0.33026397228240967, 0.3786363542079925, 0.46099493503570554, 0.9311189651489258, 0.0], [0.2409549355506897, 0.8311348974704742, 0.38049153089523313, 0.9368552148342132, 0.9104359149932861, 0.0], [0.22517320513725278, 0.7295086562633515, 0.35199616551399227, 0.8581309616565704, 0.9079555869102478, 0.0], [0.509332823753357, 0.16211927831172943, 0.678995442390442, 0.2507202297449112, 0.8845471143722534, 0.0], [0.8918281033635139, 0.359416526556015, 0.9418209597468375, 0.5050676882266998, 0.8670594096183777, 0.0], [0.13428189754486083, 0.22141119837760925, 0.23520941734313966, 0.2884054481983185, 0.8528635501861572, 0.0], [0.3410702019929886, 0.3611745774745941, 0.4340797632932663, 0.558493810892105, 0.8483645915985107, 0.0], [0.7241697609424591, 0.07349232137203217, 0.8059853255748749, 0.12879067957401275, 0.8442279696464539, 0.0], [0.6255776345729828, 0.0848228543996811, 0.7324755728244782, 0.146994486451149, 0.8437628746032715, 0.0], [0.653466972708702, 0.670866173505783, 0.746815600991249, 0.820464926958084, 0.8422113656997681, 0.0], [0.6650887668132782, 0.5841597139835358, 0.7750390827655792, 0.768796867132187, 0.8336865901947021, 0.0], [0.2169145882129669, 0.21263003945350648, 0.3436411082744598, 0.3021322667598724, 0.8271554112434387, 0.0], [0.4619706332683563, 0.05729991793632507, 0.6198791325092315, 0.14921229481697082, 0.8270950317382812, 0.0], [0.06911774277687073, 0.6581771194934845, 0.155986088514328, 0.7640855491161346, 0.8267779350280762, 0.0], [0.3990143120288849, 0.14327797889709473, 0.49909006953239443, 0.35340886116027836, 0.8233563899993896, 0.0], [0.8789778590202332, 0.5045474946498871, 0.94303218126297, 0.6238326132297516, 0.8230924606323242, 0.0], [0.3704736530780792, 0.829938891530037, 0.5245399653911591, 0.914329144358635, 0.8186348080635071, 0.0], [0.02738518118858338, 0.28757553100585936, 0.10491183400154114, 0.3996100902557373, 0.8149338364601135, 0.0], [0.797269806265831, 0.09430788457393648, 0.8423305660486221, 0.17682687342166903, 0.8068960309028625, 0.0], [0.03154720366001129, 0.4114041835069656, 0.09893070161342621, 0.4865117520093918, 0.8057674169540405, 0.0], [0.6097052663564682, 0.05152719318866729, 0.7083381563425064, 0.12496560513973236, 0.7765578627586365, 0.0], [0.08852570354938508, 0.7560727655887604, 0.18432852923870086, 0.8482656896114349, 0.7733961343765259, 0.0], [0.8717862963676453, 0.23248609304428097, 0.9263553738594055, 0.3671873688697814, 0.768665611743927, 0.0], [0.18057649135589598, 0.7914771914482117, 0.2740844964981079, 0.8918428540229798, 0.6631293892860413, 0.0], [0.043877321481704715, 0.49001536369323734, 0.08380160927772523, 0.6480004787445068, 0.6335869431495667, 0.0], [0.024194097518920904, 0.3770942836999893, 0.09230124950408936, 0.4345268100500107, 0.6028335690498352, 0.0], [0.05362071692943572, 0.6374618589878083, 0.11426236927509306, 0.7620976388454438, 0.5033589005470276, 0.0]]"}
================ pig_count: 27 ================

================ 20190621141547.jpg ================
response:  {"det_result": "[[0.25542197823524476, 0.3353059649467468, 0.4001975476741791, 0.46317635774612426, 0.9657758474349976, 0.0], [0.19315977990627287, 0.19535972476005556, 0.27108272612094875, 0.33660319447517395, 0.949517011642456, 0.0], [0.43480150699615483, 0.3039972484111786, 0.5892340421676636, 0.4782595932483673, 0.909212052822113, 0.0], [0.37013662457466123, 0.8164689779281616, 0.5137144267559051, 0.9206547021865845, 0.8970624804496765, 0.0], [0.22979669570922853, 0.7306497871875763, 0.35400352478027347, 0.8579780280590058, 0.888817310333252, 0.0], [0.5079127192497254, 0.15616052746772766, 0.6740846753120422, 0.2519838035106659, 0.8762063384056091, 0.0], [0.8885972797870636, 0.35916802287101746, 0.9409824550151825, 0.5116722404956817, 0.8757234811782837, 0.0], [0.3222222745418548, 0.18495855331420902, 0.38973417878150934, 0.34347743988037116, 0.8678868412971497, 0.0], [0.6322253465652465, 0.09085698425769807, 0.7458428144454956, 0.17094678580760958, 0.8662753701210022, 0.0], [0.8779263228178024, 0.5219457924365997, 0.9453038483858108, 0.6253760993480681, 0.8568877577781677, 0.0], [0.5138076961040497, 0.8030386507511139, 0.6839913189411164, 0.9039411008358001, 0.8443552851676941, 0.0], [0.7182290017604828, 0.0744344174861908, 0.8086081564426422, 0.12769191861152648, 0.8384566307067871, 0.0], [0.1342449128627777, 0.7035930752754211, 0.24380694031715394, 0.8636772990226745, 0.8185152411460876, 0.0], [0.041655927896499634, 0.24391731023788454, 0.11607009768486024, 0.3222251534461975, 0.8157849907875061, 0.0], [0.6842417269945145, 0.600456154346466, 0.769045302271843, 0.8204650759696961, 0.807222843170166, 0.0], [0.04178522527217866, 0.428575050830841, 0.09567042887210847, 0.5276386141777039, 0.7973988652229309, 0.0], [0.8679279178380966, 0.2271733820438385, 0.9221431881189347, 0.3715844571590423, 0.7918534278869629, 0.0], [0.10267244279384613, 0.19571231603622435, 0.18719500601291655, 0.27740641832351687, 0.7810215353965759, 0.0], [0.7959055691957474, 0.09352061152458191, 0.8447329729795456, 0.17925546765327455, 0.7788087129592896, 0.0], [0.4553974390029907, 0.060482102632522586, 0.6319695234298706, 0.14058579802513121, 0.7483526468276978, 0.0], [0.15876931250095366, 0.14991192817687987, 0.22859269082546232, 0.26780047416687014, 0.7464203238487244, 0.0], [0.6014808595180511, 0.056060454249382025, 0.7039685308933258, 0.12097258865833282, 0.7415891289710999, 0.0], [0.05432936996221543, 0.6389926671981812, 0.1036943569779396, 0.7548634767532348, 0.7370787262916565, 0.0], [0.08496533930301667, 0.7542163580656052, 0.16024259030818938, 0.8530056267976761, 0.6618684530258179, 0.0], [0.08317945897579193, 0.6818564742803573, 0.15303505957126617, 0.7622250229120254, 0.5794874429702759, 0.0], [0.04344537556171417, 0.5141217648983002, 0.08364923894405366, 0.6476760447025299, 0.504276692867279, 0.0]]"}
================ pig_count: 26 ================

================ 20190621141550.jpg ================
response:  {"det_result": "[[0.6838599711656571, 0.6606208086013794, 0.7710892170667649, 0.8272748708724975, 0.9402938485145569, 0.0], [0.26520926952362056, 0.32953397631645204, 0.38649857044219965, 0.4697645485401154, 0.8982011675834656, 0.0], [0.5156374216079712, 0.15312602519989013, 0.6798028707504273, 0.2708028078079224, 0.8904911875724792, 0.0], [0.36130602955818175, 0.8099759340286256, 0.5101854026317596, 0.9193880796432495, 0.8739372491836548, 0.0], [0.1700303077697754, 0.15172920227050782, 0.23570561408996582, 0.2642632484436035, 0.8728594779968262, 0.0], [0.1329492390155792, 0.21252053380012514, 0.24662813544273374, 0.3257600009441376, 0.8699913620948792, 0.0], [0.8888531982898712, 0.3569968342781067, 0.9418507277965545, 0.5080092310905456, 0.8673768639564514, 0.0], [0.5139020681381226, 0.8026381134986877, 0.6852060556411743, 0.9051722884178162, 0.8656722903251648, 0.0], [0.23541388511657715, 0.7340538442134857, 0.35212721824646, 0.8585911333560944, 0.859419047832489, 0.0], [0.719459256529808, 0.07310810685157776, 0.8092071443796157, 0.12624335885047913, 0.8516564965248108, 0.0], [0.34085788726806643, 0.3349116802215576, 0.5023260116577148, 0.44398775100708004, 0.8464704751968384, 0.0], [0.24616360664367676, 0.13308675289154054, 0.35294475555419924, 0.2814420938491822, 0.8323164582252502, 0.0], [0.795803265273571, 0.09264526665210723, 0.8423913910984994, 0.17893531024456022, 0.8284755349159241, 0.0], [0.4587976574897766, 0.06322473287582397, 0.6270232081413268, 0.14883238077163696, 0.8243702054023743, 0.0], [0.326967653632164, 0.06881043910980225, 0.4206260830163956, 0.2294994354248047, 0.8068063259124756, 0.0], [0.8782558888196945, 0.5038030922412873, 0.943597748875618, 0.6235027015209198, 0.8011397123336792, 0.0], [0.867403370141983, 0.22882308959960937, 0.9206940114498138, 0.3692127227783203, 0.7902088761329651, 0.0], [0.03723717927932739, 0.4061479508876801, 0.0984946608543396, 0.5185569822788239, 0.7802959084510803, 0.0], [0.11167682707309723, 0.763188025355339, 0.1834775060415268, 0.8457253962755203, 0.7796980142593384, 0.0], [0.04055920243263245, 0.23195657432079317, 0.11710016131401063, 0.3247019797563553, 0.7576957941055298, 0.0], [0.6161630868911743, 0.07711478769779206, 0.7365776777267455, 0.16915811002254488, 0.7339129447937012, 0.0], [0.05336735397577286, 0.6376380324363708, 0.10140782445669175, 0.7546170830726624, 0.7209601998329163, 0.0], [0.13452087640762328, 0.7048075258731842, 0.24099754095077514, 0.8507577359676362, 0.7165915369987488, 0.0], [0.17935211658477784, 0.7974438011646271, 0.2714140176773071, 0.897455757856369, 0.6387768387794495, 0.0], [0.08230576813220977, 0.6784022957086563, 0.15640814006328582, 0.7686613410711288, 0.6189611554145813, 0.0], [0.08143793940544128, 0.7604445695877075, 0.1541825830936432, 0.848276400566101, 0.602925181388855, 0.0]]"}
================ pig_count: 26 ================

================ 20190621141553.jpg ================
response:  {"det_result": "[[0.25505531430244444, 0.1648145318031311, 0.36948043704032896, 0.319969117641449, 0.9663053750991821, 0.0], [0.6804072797298432, 0.6567524552345275, 0.7649277269840241, 0.8261979460716247, 0.9214552640914917, 0.0], [0.5162991523742676, 0.1550707459449768, 0.6786110877990723, 0.26980427503585813, 0.89951092004776, 0.0], [0.04029585719108582, 0.39804551005363464, 0.09393433928489686, 0.5120114624500275, 0.8869109749794006, 0.0], [0.2331909120082855, 0.7339452266693115, 0.35462484955787654, 0.8563205242156983, 0.8849216103553772, 0.0], [0.8875470131635665, 0.35947387814521786, 0.9421267539262771, 0.5058832347393035, 0.8830375671386719, 0.0], [0.35890615582466123, 0.8096627533435822, 0.5082674205303193, 0.9209826171398163, 0.8803096413612366, 0.0], [0.22905958890914918, 0.32565538287162776, 0.3996945500373841, 0.466394692659378, 0.8800082206726074, 0.0], [0.3235291659832001, 0.09731526970863341, 0.46806238293647767, 0.2023240029811859, 0.8659636378288269, 0.0], [0.7194619923830032, 0.07266746759414673, 0.8077177256345749, 0.12683988809585572, 0.8515225648880005, 0.0], [0.5173878550529479, 0.8031063377857208, 0.6822316288948058, 0.9041860282421113, 0.8419069051742554, 0.0], [0.7942464396357537, 0.09258331954479218, 0.8421867802739144, 0.17845857441425322, 0.8290656208992004, 0.0], [0.8780211091041564, 0.5133154094219208, 0.9525304198265075, 0.6248787701129913, 0.8264977335929871, 0.0], [0.1312229812145233, 0.23110288381576538, 0.26738985180854796, 0.32273465394973755, 0.8258971571922302, 0.0], [0.1273337364196777, 0.7012694180011749, 0.24159545898437498, 0.8553301990032196, 0.8090124130249023, 0.0], [0.869355183839798, 0.2267285704612732, 0.9228637874126435, 0.37382589578628544, 0.7690571546554565, 0.0], [0.1645243227481842, 0.16016942262649536, 0.23051308989524844, 0.2507018446922302, 0.7572027444839478, 0.0], [0.4552234292030334, 0.06282475888729096, 0.6467123389244078, 0.14914280474185942, 0.7095248699188232, 0.0], [0.6207995533943176, 0.07808120846748351, 0.7318315386772155, 0.17110306620597837, 0.6961165070533752, 0.0], [0.08310246467590332, 0.7593006700277328, 0.16655261516571046, 0.8486085325479508, 0.6946851015090942, 0.0], [0.0550129920244217, 0.6377000391483307, 0.10035936534404755, 0.7601681172847748, 0.6907160878181458, 0.0], [0.1823414504528046, 0.8208630412817001, 0.2753485023975373, 0.8927535206079482, 0.6773250102996826, 0.0], [0.03336356282234192, 0.33990943133831025, 0.09926139712333679, 0.4163350373506546, 0.6322934031486511, 0.0], [0.09137872457504273, 0.6876684784889221, 0.1576262593269348, 0.7882758498191833, 0.5370994806289673, 0.0]]"}
================ pig_count: 24 ================

================ 20190621141702.jpg ================
response:  {"det_result": "[[0.22350141406059268, 0.6762887954711914, 0.3731423199176789, 0.8184487342834472, 0.9548922181129456, 0.0], [0.3554376900196075, 0.8033478677272797, 0.5178024947643279, 0.916188532114029, 0.9342366456985474, 0.0], [0.41963348984718324, 0.10559765100479125, 0.5215966165065765, 0.31351484060287477, 0.9148365259170532, 0.0], [0.24928047060966493, 0.327079701423645, 0.40166056752204893, 0.4416670560836792, 0.8924790620803833, 0.0], [0.5149345755577087, 0.17052462100982668, 0.6779902100563049, 0.29205095767974854, 0.8909578323364258, 0.0], [0.5388258635997771, 0.7447358965873718, 0.6867108643054961, 0.8399172902107239, 0.8849926590919495, 0.0], [0.71777563393116, 0.06494015455245972, 0.7983715027570725, 0.12339491844177246, 0.8744017481803894, 0.0], [0.7954665750265122, 0.5785638570785522, 0.8826254278421403, 0.7036791086196899, 0.8737918138504028, 0.0], [0.6637972176074982, 0.6482859671115876, 0.8199613273143769, 0.7434307992458344, 0.8732413649559021, 0.0], [0.8661074936389923, 0.22600043416023252, 0.9228401839733124, 0.3657041251659393, 0.8627683520317078, 0.0], [0.7602462828159332, 0.11995237469673156, 0.8734313905239105, 0.23398701548576356, 0.8567670583724976, 0.0], [0.8956452071666717, 0.3657357215881347, 0.9450255692005157, 0.5135135650634766, 0.8445569276809692, 0.0], [0.14634484350681304, 0.7393070816993714, 0.23839896619319914, 0.8807906508445741, 0.8305044770240784, 0.0], [0.8794899225234986, 0.5026386678218842, 0.9294854879379273, 0.634317833185196, 0.8270094394683838, 0.0], [0.5092974722385407, 0.815280893445015, 0.6741485536098482, 0.9056802958250046, 0.8193835616111755, 0.0], [0.07616996467113496, 0.21829421520233155, 0.15875621140003204, 0.32190282344818116, 0.8052489757537842, 0.0], [0.6853458523750305, 0.07137364149093627, 0.7411078333854676, 0.2028606295585632, 0.7820446491241455, 0.0], [0.07674590349197388, 0.7687113344669342, 0.14894877672195433, 0.8493100583553314, 0.7341012954711914, 0.0], [0.039960877597332, 0.3126288890838623, 0.08451076298952104, 0.4022897243499756, 0.7196946144104004, 0.0], [0.06600799262523652, 0.6542474508285523, 0.16344936192035675, 0.8114694833755494, 0.6840709447860718, 0.0], [0.5587529957294464, 0.06180830597877503, 0.7073469340801238, 0.2052306354045868, 0.5386325716972351, 0.0], [0.6123762965202332, 0.05824828445911408, 0.7150348782539367, 0.12364704310894013, 0.5344389081001282, 0.0]]"}
================ pig_count: 22 ================

四、本章小结

本章我们介绍了如何使用ModelBox开发一个AI智能数猪的原创应用，我们只需要在之前的基础上重新训练一个猪只目标检测模型进行替换，之后修改配置文件和工程的流程图即可进行视频推理。同时我们可以了解到图片标注、数据处理和模型训练方法，以及对应的推理应用逻辑。

点击关注，第一时间了解华为云新鲜技术~

微信关注我们

原文链接：https://my.oschina.net/u/4526289/blog/11212427

转载内容版权归作者及来源网站所有！

低调大师中文资讯倾力打造互联网数据资讯、行业资源、电子商务、移动互联网、网络营销平台。持续更新报道IT业界、互联网、市场资讯、驱动更新,是最及时权威的产业资讯及硬件资讯报道平台。

技术解读数据库如何实现“多租户”？

本文分享自华为云社区《【GaussTech速递】技术解读之GaussDB多租技术》，作者：GaussDB数据库。数据库多租技术介绍随着云计算时代的到来，多租户的概念也逐渐广为人知。“多租户”使得租户之间可以共享物理资源，能够帮助用户节约硬件成本和运维成本，提高资源利用效率。同时，在实现的过程中，考虑到共享带来的安全、隔离等问题以及后续业务面临的扩展需求，“多租户”在隔离性和扩展性方面也进行了相应的设计实现。那么，在数据库领域是如何实现“多租户”呢？业界有虚拟机多租、容器多租、数据库内核多租等多种技术可以实现多租户。虚拟机多租和容器多租，顾名思义就是在一台物理服务器上部署多个虚拟机或者容器，然后在虚拟机或者容器内进行数据库服务的部署。这类技术方案在安全性和隔离性方面具有天然的优势。数据库内核多租，是由数据库内核提供的多租户特性。相比于虚拟机多租和容器多租，内核多租没有虚拟化管理层、OS（Operating System，简称操作系统）层、数据库公共层的额外开销，而且底噪小，在资源整合、资源的弹性伸缩等方面具备天然优势。数据库内核多租通过将数据库内核语义与成熟的资源隔离技术栈相...

2024-06-20

350

众所周知，配置即代码≠基础设置即代码

前段时间翻到几条留言，问： “配置即代码和基础设施即代码一样吗？” “配置即代码是什么？怎么都是基础设施即代码？” 我们都是知道，DevOp的快速发展，让服务器管理与配置的时间大大减少，配置即代码和基础设施即代码作为DevOps的重要实践，在其中起到了关键性作用。不少人将二者看作是一件事，配置即大代码是关于管理特定的应用程序配置设置本身，而基础设施即代码更关注的是部署支持应用程序环境所需的底层基础设施。二者虽然相互补充，经常一起使用，但为了避免混淆，我将从概念、意义以及做法三个方面介绍配置即代码。一、什么是配置即代码？配置即代码（Configuration as Code，CaC）是不同环境之间配置的版本迁移。在配置即代码的实践中，配置信息通常以文本文件的形式存储，这些文件可以用版本控制系统（如Git）进行管理。通过这种方式，每次环境配置的变更都可以被追踪和审查，有助于团队协作和问题的快速定位。配置即代码一般用于管理软件包和组件的设置。这适用于广泛的行业。在应用程序开发过程中，可能会使用配置来支持多种操作系统。通过维护配置即代码，您可以跟踪数百甚至数千个硬件原理图和嵌入式开...

2024-06-24

241

发表评论

资源下载

更多资源

Mario

马里奥是站在游戏界顶峰的超人气多面角色。马里奥靠吃蘑菇成长，特征是大鼻子、头戴帽子、身穿背带裤，还留着胡子。与他的双胞胎兄弟路易基一起，长年担任任天堂的招牌角色。

Oracle

Oracle Database，又名Oracle RDBMS，或简称Oracle。是甲骨文公司的一款关系数据库管理系统。它是在数据库领域一直处于领先地位的产品。可以说Oracle数据库系统是目前世界上流行的关系数据库管理系统，系统可移植性好、使用方便、功能强，适用于各类大、中、小、微机环境。它是一种高效率、可靠性好的、适应高吞吐量的数据库方案。

Eclipse

Eclipse 是一个开放源代码的、基于Java的可扩展开发平台。就其本身而言，它只是一个框架和一组服务，用于通过插件组件构建开发环境。幸运的是，Eclipse 附带了一个标准的插件集，包括Java开发工具（Java Development Kit，JDK）。

Sublime Text

Sublime Text具有漂亮的用户界面和强大的功能，例如代码缩略图，Python的插件，代码段等。还可自定义键绑定，菜单和工具栏。Sublime Text 的主要功能包括：拼写检查，书签，完整的 Python API ， Goto 功能，即时项目切换，多选择，多窗口等等。Sublime Text 是一个跨平台的编辑器，同时支持Windows、Linux、Mac OS X等操作系统。