基于flask部署yolov5 web服务（1）

本文基于官网的yolov5通过flask框架将模型推断通过webserve的形式部署，客户端上传待检测的图片，服务器返回处理后的结果（结果可以是模型直接输出的字符串信息也可以是经过后处理画好框的图片），只是整体流程跑通，很多需要优化的地方。
代码：

#本代码整体就是在yolov5源码的detect.py上进行修改
import io
import json
import numpy as np
from torchvision import models
import torchvision.transforms as transforms
from PIL import Image
#导入flask相关
from flask import Flask, jsonify, request

#yolov5中detect.py中的引用
import argparse
import os
import shutil
import time
from pathlib import Path

import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random

from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import (
    check_img_size, non_max_suppression, apply_classifier, scale_coords,
    xyxy2xywh, plot_one_box, strip_optimizer, set_logging)
from utils.torch_utils import select_device, load_classifier, time_synchronized

#网络传输图片通常使用base64编码，客户端把图片encode成字符串，
#服务器接受字符串decoder成图片后送入yolov5的模型进行推断
import base64

#推断用的参数

#加载模型，通用操作，不用管
app = Flask(__name__)

#下面定义base64的编码和解码函数
#图片编码函数
def image_to_base64(full_path):
    with open(full_path, "rb") as f:
        data = f.read()
        image_base64_enc = base64.b64encode(data)
        image_base64_enc = str(image_base64_enc, 'utf-8')
    return image_base64_enc

#解码，可以参考链接：https://blog.csdn.net/ctwy291314/article/details/91493156
def base64_to_image(base64_code): 
    # base64解码
    img_data = base64.b64decode(base64_code)
    # 转换为np数组
    img_array = np.fromstring(img_data, np.uint8)
    # 转换成opencv可用格式
    image_base64_dec = cv2.imdecode(img_array, cv2.COLOR_RGB2BGR)
    return image_base64_dec

#yolov5推断（检测）函数，和yolov5中源码相同
def detect(source, save_img=True):
    #各种传参数
    out,  weights, view_img, save_txt, imgsz = \
        opt.output, opt.weights, opt.view_img, opt.save_txt, opt.img_size

    # Initialize
    set_logging()
    device = select_device(opt.device)
    if os.path.exists(out):
        shutil.rmtree(out)  # delete output folder
    os.makedirs(out)  # make new output folder
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
    if half:
        model.half()  # to FP16

    # Second-stage classifier
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model'])  # load weights
        modelc.to(device).eval()

    # Set Dataloader
    vid_path, vid_writer = None, None
    #if save_img = True：
    dataset = LoadImages(source, img_size=imgsz)

    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))]

    # Run inference
    t0 = time.time()
    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        t1 = time_synchronized()
        pred = model(img, augment=opt.augment)[0]

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections
        for i, det in enumerate(pred):  # detections per image
            #if webcam:  # batch_size >= 1
            #    p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
            if 1:
                p, s, im0 = path, '', im0s

            save_path = str(Path(out) / Path(p).name)
            txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '')
            s += '%gx%g ' % img.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            if det is not None and len(det):
                print("line129")
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += '%g %ss, ' % (n, names[int(c)])  # add to string

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format

                    if save_img or view_img:  # Add bbox to image
                        label = '%s %.2f' % (names[int(cls)], conf)
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
            print('%sDone. (%.3fs)' % (s, t2 - t1))

    #im0是画好框的检测结果图，此处为了验证可以把im0存下来看看
    #cv2.imwrite("./serve_res.png", im0)
    return im0

#说明webserve的服务类型，客户端call服务器不能只指定ip地址，还要加这个服务绑定（下文有说明）
@app.route('/predict', methods=['POST'])
def predict():
    if request.method == 'POST':
        file = request.files['file']
        img_bytes = file.read()
        #cv2.imwrite("clint-img.png", np.array(Image.open(io.BytesIO(img_bytes))))
        #调用检测函数 
        res_image = detect("clint-img.png")
        json_res = image_to_base64("./serve_res.png")

    #jsonify中保存着结果图片的base编码，拿下来客户端解码即可得到结果图片
    return jsonify({'detect_res':json_res})
    
        #class_id, class_name = get_prediction(image_bytes=img_bytes)
        #return jsonify({'class_id': class_id, 'class_name': class_name})


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
    #source不需要，直接从客户端传入
    #parser.add_argument('--source', type=str, default='inference/images', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--output', type=str, default='inference/output', help='output folder')  # output folder
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    opt = parser.parse_args()
    #接受clint图像作为source
    #source = 客户端传图
    #app.run(host='192.168.0.0',port= 6000,debug=True)
    #改成运行机器的ip地址
    app.run(debug=True,host='192.168.13.134',port=5001)

后面将介绍客户端请求服务器并显示检测图片结果。