深度检测模型部署-测试版

链接：源代码

提取码：7gpf

B站视频：第一次讲，有很多问题，也先放在这里吧，麦克分问题，声音很小

上：https://www.bilibili.com/video/BV19f4y1y7xd?from=search&seid=4295823664546149809

下：https://www.bilibili.com/video/BV1qK411p72Q?from=search&seid=4295823664546149809

深 度 检 测 模 型 部 署 − 测 试 版 深度检测模型部署-测试版 深度检测模型部署−测试版

• 1.技术框架及编码逻辑
• 2.一测
• 3.二测
• 4.补充

1.技术框架及编码逻辑

技术框架：

Pytorch-GPU 、Flask
           

编码逻辑：

#------------------------------------------------------0.引入库--------------------------------------------------------------

#------------------------------------------------------1.加载模型--------------------------------------------------------------

#------------------------------------------------------2.获取Inference数据--------------------------------------------------------------

#------------------------------------------------------3.定义数据预处理--------------------------------------------------------------

#------------------------------------------------------4.模型预测--------------------------------------------------------------

#------------------------------------------------------5.服务返回--------------------------------------------------------------

#------------------------------------------------------6.主函数--------------------------------------------------------------




           

2.一测

服务端：Server.py

# -*- coding: utf-8 -*-
# 导入常用的库
import time
import os
import torch
from PIL import Image
import torchvision.transforms as transforms
# 导入flask库的Flask类和request对象
from flask import request, Flask
app = Flask(__name__)

BASE_DIR = os.path.dirname(os.path.abspath(__file__))

# # 定义字典className_list，把种类索引转换为种类名称
# className_list = ['__background__', 'wheat_head']

#------------------------------------------------------1.加载模型--------------------------------------------------------------
path_model="./saved_model/model2.pkl"
model_loaded=torch.load(path_model)

#------------------------------------------------------2.获取测试图片--------------------------------------------------------------

# img_dir=os.path.join(BASE_DIR ,"data", "global-wheat-detection","test")
# names = [name for name in list(filter(lambda x: x.endswith(".jpg"), os.listdir(img_dir)))]
#path_img = os.path.join(BASE_DIR ,"data", "global-wheat-detection","test",i)

# 根据图片文件路径获取图像数据矩阵
def get_imageNdarray(imageFilePath):
    input_image = Image.open(imageFilePath).convert("RGB")
    return input_image


#------------------------------------------------------3.定义图片预处理--------------------------------------------------------------
# 模型预测前必要的图像处理
def process_imageNdarray(input_image):
    preprocess = transforms.Compose([
        transforms.ToTensor(),
    ])
    img_chw = preprocess(input_image)
    return img_chw  # chw:channel height width

#------------------------------------------------------4.模型预测--------------------------------------------------------------
# 使用模型对指定图片文件路径完成图像分类，返回值为预测的种类名称
def predict_image(model, imageFilePath):
    model.eval()  # 参数固化
    input_image = get_imageNdarray(imageFilePath)
    img_chw = process_imageNdarray(input_image)
    if torch.cuda.is_available():
        img_chw = img_chw.to('cuda')
        model.to('cuda')
    input_list = [img_chw]
    with torch.no_grad():  # 不计算梯度
        output_list = model(input_list)
        output_dict = output_list[0]
        #print('对此图片路径 %s 的预测结果为 %s' % (output_dict))
        return output_dict

#------------------------------------------------------5.服务返回--------------------------------------------------------------
# 定义回调函数，接收来自/的post请求，并返回预测结果
@app.route("/", methods=['POST'])
def return_result():
    startTime = time.time()
    received_file = request.files['file']
    imageFileName = received_file.filename
    if received_file:
        received_dirPath = './resources/received_images'
        if not os.path.isdir(received_dirPath):
            os.makedirs(received_dirPath)
        imageFilePath = os.path.join(received_dirPath, imageFileName)
        received_file.save(imageFilePath)
        print('图片文件保存到此路径：%s' % imageFilePath)
        usedTime = time.time() - startTime
        print('接收图片并保存，总共耗时%.2f秒' % usedTime)
        startTime = time.time()
        print(imageFilePath)
        result = predict_image(model_loaded, imageFilePath)
        result = str(result)
        print(result)
        usedTime = time.time() - startTime
        print('完成对接收图片的检测，总共耗时%.2f秒' % usedTime)
        print("testtest",result)
        return result
    else:
        return 'failed'


# 主函数
if __name__ == "__main__":
    #print('在开启服务前，先测试predict_image函数')
    # imageFilePath = os.path.join(BASE_DIR, "data", "global-wheat-detection", "test", "51b3e36ab.jpg")
    # result = predict_image(model_loaded, 'D:\\PycharmWorkPlaces\\DeepModel_deploy_flask\\data\\global-wheat-detection\\test\\51b3e36ab.jpg')
    # print(result)
    app.run("127.0.0.1", port=5000)

           

客户端：Client.py

import requests
import os

BASE_DIR = os.path.dirname(os.path.abspath(__file__))


# 主函数
if __name__ == "__main__":
    url = "http://127.0.0.1:5000"
    while True:
        input_content = input('输入图片路径，输入-1退出，默认值os.path.join(BASE_DIR, "data", "global-wheat-detection", "test", "51b3e36ab.jpg") ')
        if input_content.strip() == "":
            input_content = 'D:\\PycharmWorkPlaces\\DeepModel_deploy_flask\\data\\global-wheat-detection\\test\\51b3e36ab.jpg'
        if input_content.strip() == "-1":
            break
        elif not os.path.exists(input_content.strip()):
            print('输入图片路径不正确，请重新输入')
        else:
            imageFilePath = input_content.strip()
            imageFileName = os.path.split(imageFilePath)[1]
            file_dict = {
                'file':(imageFileName,
                    open(imageFilePath,'rb'),
                    'image/jpg')}
            result = requests.post(url, files=file_dict)
            predict_result = result.text
            print('图片路径:%s 预测结果为:%s\n' %(imageFilePath, predict_result))
           

3.二测（客户端为页面）

服务端：Server2.py

# -*- coding: utf-8 -*-
# 导入常用的库
import time
import os
import torch
from PIL import Image
import torchvision.transforms as transforms
import json
# 导入flask库的Flask类和request对象
from flask import Flask, render_template, request, jsonify
app = Flask(__name__)

BASE_DIR = os.path.dirname(os.path.abspath(__file__))

# # 定义字典className_list，把种类索引转换为种类名称
# className_list = ['__background__', 'wheat_head']

#------------------------------------------------------1.加载模型--------------------------------------------------------------
path_model="./saved_model/model2.pkl"
#model_loaded=torch.load(path_model,map_location='cpu') # 只有cpu加载模型
model_loaded=torch.load(path_model)
#------------------------------------------------------2.获取测试图片--------------------------------------------------------------

# img_dir=os.path.join(BASE_DIR ,"data", "global-wheat-detection","test")
# names = [name for name in list(filter(lambda x: x.endswith(".jpg"), os.listdir(img_dir)))]
#path_img = os.path.join(BASE_DIR ,"data", "global-wheat-detection","test",i)

# 根据图片文件路径获取图像数据矩阵
def get_imageNdarray(imageFilePath):
    input_image = Image.open(imageFilePath).convert("RGB")
    return input_image


#------------------------------------------------------3.定义图片预处理--------------------------------------------------------------
# 模型预测前必要的图像处理
def process_imageNdarray(input_image):
    preprocess = transforms.Compose([
        transforms.ToTensor(),
    ])
    img_chw = preprocess(input_image)
    return img_chw  # chw:channel height width

#------------------------------------------------------4.模型预测--------------------------------------------------------------
# 使用模型对指定图片文件路径完成图像分类，返回值为预测的种类名称
def predict_image(model, imageFilePath):
    model.eval()  # 参数固化
    input_image = get_imageNdarray(imageFilePath)
    img_chw = process_imageNdarray(input_image)
    if torch.cuda.is_available():
        img_chw = img_chw.to('cuda')
        model.to('cuda')
    input_list = [img_chw]
    with torch.no_grad():  # 不计算梯度
        output_list = model(input_list)
        output_dict = output_list[0]
        #print('对此图片路径 %s 的预测结果为 %s' % (output_dict))
        return output_dict

#------------------------------------------------------5.服务返回--------------------------------------------------------------


# 访问首页时的调用函数
@app.route('/')
def index_page():
    return render_template('index.html')


# 使用predict_image这个API服务时的调用函数
@app.route("/upload_image", methods=['POST'])
def anyname_you_like():
    startTime = time.time()
    received_file = request.files['input_image']
    imageFileName = received_file.filename
    if received_file:
        received_dirPath = '../resources/received_images'
        if not os.path.isdir(received_dirPath):
            os.makedirs(received_dirPath)
        imageFilePath = os.path.join(received_dirPath, imageFileName)
        received_file.save(imageFilePath)
        print('image file saved to %s' % imageFilePath)
        usedTime = time.time() - startTime
        print('接收图片并保存，总共耗时%.2f秒' % usedTime)
        startTime = time.time()
        result = predict_image(model_loaded, imageFilePath)
        result = str(result)
        usedTime = time.time() - startTime
        print('完成对接收图片的预测，总共耗时%.2f秒' % usedTime)
        # return result
        return render_template("result.html",result=result)
    else:
        return 'failed'



# 主函数
if __name__ == "__main__":
    # print('在开启服务前，先测试predict_image函数')
    # imageFilePath = 'D:\\PycharmWorkPlaces\\DeepModel_deploy_flask\\data\\global-wheat-detection\\test\\51b3e36ab.jpg'
    # result = predict_image(model_loaded, imageFilePath)
    app.run("127.0.0.1", port=5000)
           

客户端：index.html

<!DOCTYPE html>
<html lang="en">
    <head>
        <meta charset="UTF-8">
        <title>测试</title>
    </head>
    <body>
        <div>
            <form method="post" action="http://localhost:5000/upload_image" enctype="multipart/form-data">
               <input type="file"  value="选择检测图片" size="22" id="select_files" name="input_image" onchange="show_selectedImage()"/>
               <br>
               <canvas id="image_canvas" height="1020" width="1020"></canvas>
               <text name="image_className" value=""/>
               <br>
               <input type="submit" class="button-new" value="提交信息" style="margin-top:15px;"/>
            </form>

            <script type="text/javascript">
                function show_selectedImage(){
                    /// get select files.
                    var selected_files = document.getElementById("select_files").files;
                    for(var file of selected_files){
                        console.log(file.webkitRelativePath);
                        /// read file content.
                        var reader = new FileReader();
                        reader.readAsDataURL(file);
                        reader.onloadend = function(){
                            /// deal data.
                            var img = new Image();
                            /// after loader, result storage the file content result.
                            img.src = this.result;
                            img.onload = function(){
                                var canvas = document.getElementById("image_canvas");
                                var cxt = canvas.getContext('2d');
                                cxt.drawImage(img, 0, 0);
                            }
                        }
                    }
                }
            </script>
        </div>
    </body>
</html>
           

返回结果网页：result.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>返回结果</title>
</head>
<body>
<h1>返回结果是：</h1>


{{ result }}

</body>
</html>
           

4.补充

图像识别工程的工作步骤:

• 1.数据准备:

  1.1拍摄照片或者下载数据集;

  1.2图像标注;

  1.3图像数据处理(图像合成、图像剪裁、图像改变像素大小);

  1.4检查标注文件的正确性;

  1.5划分训练集、验证集.

• 2.模型搭建
• 3.模型训练(读取数据的多线程生成器、多GPU并行训练、保存模型)
• 4.模型评估(加载模型、使用业务对应的评估指标在验证集上计算模型效果)
• 5.模型测试(使用实际场景中的图像数据测试模型效果，单张图片检测、实时视频检测)
• 6.模型部署(web、Android、开发板)

• 7.闭环优化

  7.1根据业务使用场景在第2步优化;

  7.2根据模型在实际场景的使用效果在第3-6步之，间循环迭代

  7.2.1如果新加入的数据提高了模型在验证集上的效果，则替换模型部署使用的权重文件

  7.2.2如果替换后的新权重文件在实际场景中使用效果不好，则使用版本控制工具回退到上一-个版本的权重文件

完成搭建神经网络的要点:

1.确定网络的输入矩阵的形状;

2.确定网络的输出矩阵的形状;

3.理解网络的架构流程;

4.确定每个数据层、处理层的矩阵形状:

5.理解并实现网络计算损失的损失函数;

6.理解权重优化使用的优化器;