将pytorch模型部署到服务器（自己电脑），手机前端访问返回分类结果

后端：flask+polar+pytorch

后端采用flask，把自己的电脑作为服务器，开放5000端口

代码直接用：

使用Flask来部署PyTorch模型 - PyTorch官方教程中文版 (panchuang.net)

使用polar内网穿透：

(19条消息) 个人电脑秒变服务器 简单几步，你的电脑也可以成为服务器 （内网穿透）_小王不头秃的博客-CSDN博客_把自己电脑变成服务器

具体代码和文件：（一个app.py，一个imagenet_class_index.json,使用cors解决跨域问题） 

(31条消息) 将pytorch模型部署到服务器（自己电脑）flask-深度学习文档类资源-CSDN文库

import io
import json

from torchvision import models
import torchvision.transforms as transforms
from PIL import Image
from flask import Flask, jsonify, request
from flask_cors import CORS


app = Flask(__name__)
CORS(app, resources=r'/*')
imagenet_class_index = json.load(open('./imagenet_class_index.json'))
model = models.densenet121(pretrained=True)
model.eval()


def transform_image(image_bytes):
    my_transforms = transforms.Compose([transforms.Resize(255),
                                        transforms.CenterCrop(224),
                                        transforms.ToTensor(),
                                        transforms.Normalize(
                                            [0.485, 0.456, 0.406],
                                            [0.229, 0.224, 0.225])])
    image = Image.open(io.BytesIO(image_bytes))
    return my_transforms(image).unsqueeze(0)


def get_prediction(image_bytes):
    tensor = transform_image(image_bytes=image_bytes)
    outputs = model.forward(tensor)
    _, y_hat = outputs.max(1)
    predicted_idx = str(y_hat.item())
    return imagenet_class_index[predicted_idx]


@app.route('/predict', methods=['POST'])
def predict():
    if request.method == 'POST':
        file = request.files['file']
        img_bytes = file.read()
        class_id, class_name = get_prediction(image_bytes=img_bytes)
        return jsonify({'class_id': class_id, 'class_name': class_name})


if __name__ == '__main__':
    app.run()

前端:uniapp

前端采用uniapp，发送post请求，直接把图片发送给后端

<template>
	<view>
		<input type="text" value="" v-model="username" placeholder="账号"/>
		<input type="text" value="" v-model="password" placeholder="密码"/>
		<!-- <button type="default" @click="request()">发起请求</button> -->
		<button type="default" @click="request()">发起请求/登录</button>
		<button type="default" @click="upload()">上传图片</button>
		<view class="arrow-area">
			{{msg}} <br>
			
			
		</view>
		<button type="default" @click="nextPage()">进入个人中心</button>
	</view>
</template>

<script>
	export default {
		data() {
			return {
				"msg":'显示信息',
				"nickName": '',
				"age":20,
				"email":'',
				"id":'',
				
				"username":"",
				"password":"",
				
			}
		},
		methods: {
			
			request(){
				
				var that = this
				uni.request({
					method:'POST',
					header: {
						// json数据的发送
						// "content-type": "application/json",
						// 键值对形式数据发送
						"content-type": "application/x-www-form-urlencoded",
						"source": "fromApp",
						// "Authorization":"Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6MjEsInVzZXJuYW1lIjoiMjIyMjIyIiwicGFzc3dvcmQiOiIiLCJuaWNrbmFtZSI6bnVsbCwiZW1haWwiOm51bGwsInVzZXJfcGljIjoiIiwiaWF0IjoxNjU5OTQyODg0LCJleHAiOjE2NTk5Nzg4ODR9.-7TwtvLhXkU_iGJ9HnSG8K4vSRlUFj1mie1O-EeKU5Q"
					},
					// dataType:JSON,
					// url:'http://http://111.67.196.136:80/api/reguser',
					// url:'http://127.0.0.1:3007/api/login',
					// url:'http://127.0.0.1:3007/my/userinfo', 
					url:'http://127.0.0.1:5000/predict',
					
					data:{
													
						// "message" :that.msg ,						
						// "nickName": "zs",
						// "age":20,
						
						// "username":that.username,
						// "password":that.password,
						
						
						
						
						
						
						 
					},
					success:(res)=> {
						console.log('请求成功！success')
						console.log(res.data)
						// that.msg =JSON.stringify(res.data) 
						that.msg =res.data
						// that.nickName =res.data.data.nickname
						// that.username =res.data.data.username
						// that.id =res.data.data.id
						var token = res.data.token
						// console.log(token)
						uni.setStorageSync('token',token)
						
						
					}
				})
			},
			nextPage(){
				uni.navigateTo({
					url:'video_play'
				})
			},
			upload(){
				uni.chooseImage({
					success: (chooseImageRes) => {
						const tempFilePaths = chooseImageRes.tempFilePaths;
						uni.uploadFile({
							// url: 'http://127.0.0.1:5000/predict', //仅为示例，非真实的接口地址,
							url: 'http://7c8087d8.r3.cpolar.top/predict',//cpolar开放5000端口
							filePath: tempFilePaths[0],
							name: 'file',
							formData: {
								'user': 'test'
							},
							success: (uploadFileRes) => {
								console.log(uploadFileRes.data);
								this.msg = uploadFileRes.data
								console.log('预测结束！结果已返回')
							}
						});
					}
				});

			}


		}
	}
</script>

<style>

</style>

结果

选了家里的小狗狗：

cmd返回200，说明请求成功

 前端返回分类结果：