原文出自这里原文出处

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

`技术框架：

Pytorch-GPU 、Flask` 



`编码逻辑：` 

![](https://csdnimg.cn/release/blogv2/dist/pc/img/newCodeMoreWhite.png)

2.一测

服务端：Server.py

import time
import os
import torch
from PIL import Image
import torchvision.transforms as transforms

from flask import request, Flask
app = Flask(__name__)

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

path_model="./saved_model/model2.pkl"
model_loaded=torch.load(path_model)

def get_imageNdarray(imageFilePath):
    input_image = Image.open(imageFilePath).convert("RGB")
    return input_image

def process_imageNdarray(input_image):
    preprocess = transforms.Compose([
        transforms.ToTensor(),
    ])
    img_chw = preprocess(input_image)
    return img_chw  

def predict_image(model, imageFilePath):
    model.eval()  
    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():  
        output_list = model(input_list)
        output_dict = output_list[0]
        
        return output_dict



@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'

if __name__ == "__main__":
    
   
    
    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__))

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

import time
import os
import torch
from PIL import Image
import torchvision.transforms as transforms
import json

from flask import Flask, render_template, request, jsonify
app = Flask(__name__)

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

path_model="./saved_model/model2.pkl"

model_loaded=torch.load(path_model)

def get_imageNdarray(imageFilePath):
    input_image = Image.open(imageFilePath).convert("RGB")
    return input_image

def process_imageNdarray(input_image):
    preprocess = transforms.Compose([
        transforms.ToTensor(),
    ])
    img_chw = preprocess(input_image)
    return img_chw  

def predict_image(model, imageFilePath):
    model.eval()  
    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():  
        output_list = model(input_list)
        output_dict = output_list[0]
        
        return output_dict



@app.route('/')
def index_page():
    return render_template('index.html')

@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 render_template("result.html",result=result)
    else:
        return 'failed'

if __name__ == "__main__":
'''python
    
    
    app.run("127.0.0.1", port=5000)` 

![](https://csdnimg.cn/release/blogv2/dist/pc/img/newCodeMoreWhite.png)

```html


### 客户端：index.html

```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>` 
```html



## 返回结果网页：result.html

`

返回结果

返回结果是：

{{ result }}

` 

### 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;

* * *
# 人工智能
Logo
九章云极普惠算力

更多推荐

Webpack HMR在aspnetcore-Vue-starter中的应用：提升开发效率的秘诀

aspnetcore-Vue-starter是一个集成了ASP.NET Core后端与Vue.js前端的强大单页应用模板，它通过Webpack热模块替换（HMR）技术，为开发者提供了无缝的开发体验，让前端代码修改无需手动刷新页面即可实时生效。## 🚀 什么是Webpack HMR？Webpack热模块替换（Hot Module Replacement）是一项革命性的开发技术，它允许在应用

avatar 九章云极普惠算力

GraphQL Compose性能优化：DataLoader与批量查询最佳实践

GraphQL Compose是Node.js平台上用于构建复杂GraphQL Schema的强大工具包，通过DataLoader实现批量查询和请求合并是提升API性能的关键技术。本文将详细介绍如何在GraphQL Compose项目中应用DataLoader进行性能优化，包含具体实现方法和最佳实践指南。## 为什么需要DataLoader？在GraphQL查询中，典型的N+1查询问题会导

avatar 九章云极普惠算力

人脸识别真的需要深度学习吗？ArcFace技术深度解析

在当今数字化时代，人脸识别技术已广泛应用于安防、支付、智能门禁等领域。许多人好奇：人脸识别真的需要深度学习吗？答案是肯定的。传统方法在复杂场景下识别精度有限，而基于深度学习的ArcFace技术通过创新的角度损失函数，实现了高精度的人脸识别。本文将深入解析ArcFace技术的原理、优势及实际应用。## 一、传统方法的局限性传统人脸识别方法如 Eigenfaces、Fisherfaces 等，

avatar 九章云极普惠算力