关于用yolov5进行验证集的map计算

import argparse
import os
import platform
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
from cfg_mAP import Cfg

cfg = Cfg


def detect(save_img=False):
    out, source, weights, view_img, save_txt, imgsz = \
        opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')

    # 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 webcam:
        view_img = True
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz)
    else:
        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
    test_time=[]
    for path, img, im0s, vid_cap in dataset:

        # Inference
        t1 = time_synchronized()

        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()
            else:
                p, s, im0 = path, '', im0s

            img_name = Path(p).name

            txt = open(opt.eval_imgs_name_txt, 'a')
            txt.write(img_name[:-4])
            txt.write('\n')
            txt.close()

            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):
                # 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):
                    txt = open(opt.eval_classtxt_path + '/%s' % names[int(cls)], 'a')
                    obj_conf = conf.cpu().numpy()

                    xyxy = torch.tensor(xyxy).numpy()
                    x1 = xyxy[0]
                    y1 = xyxy[1]
                    x2 = xyxy[2]
                    y2 = xyxy[3]

                    new_box = [img_name[:-4], obj_conf, x1, y1, x2, y2]

                    txt.write(" ".join([str(a) for a in new_box]))
                    txt.write('\n')
                    txt.close()

                    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' % (cfg.textnames[int(cls)], conf)
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)

            test_time.append(t2 - t1)

            # Print time (inference + NMS)
            print('%sDone. (%.3fs)' % (s, t2 - t1))


            # Stream results
            if view_img:
                cv2.imshow(p, im0)
                if cv2.waitKey(1) == ord('q'):  # q to quit
                    raise StopIteration

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'images':
                    cv2.imwrite(save_path, im0)
                else:
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer

                        fourcc = 'mp4v'  # output video codec
                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        print('Results saved to %s' % Path(out))
        if platform.system() == 'Darwin' and not opt.update:  # MacOS
            os.system('open ' + save_path)

    print('Done. (%.3fs)' % (time.time() - t0))
    mean_time=sum(test_time)/len(test_time)
    print('mean time:', mean_time)
    print('frame: ', 1/mean_time)


if __name__ == '__main__':

    dir = '../data_test/imgs_name_manual.txt'
    if os.path.exists(dir):
        os.remove(dir)
    else:
        open(dir, 'w')

    predictions_manual='../data_test/predictions_manual'
    class_txt_manual='../data_test/class_txt_manual'
    cachedir_manual='../data_test/cachedir_manual'

    if os.path.exists(predictions_manual):
        shutil.rmtree(predictions_manual)  # delete output folder
    os.makedirs(predictions_manual)  # make new output folder

    if os.path.exists(class_txt_manual):
        shutil.rmtree(class_txt_manual)  # delete output folder
    os.makedirs(class_txt_manual)  # make new output folder

    if os.path.exists(cachedir_manual):
        shutil.rmtree(cachedir_manual)  # delete output folder
    os.makedirs(cachedir_manual)  # make new output folder

    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='../runs/train/exp/weights/last.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='../data_test/JPEGImages_manual',
                        help='source')  # file/folder, 0 for webcam
    parser.add_argument('--output', type=str, default='../data_test/predictions_manual',
                        help='output folder')  # output folder
    parser.add_argument('--eval_imgs_name_txt', type=str, default='../data_test/imgs_name_manual.txt',
                        help='output folder')  # output folder
    parser.add_argument('--eval_classtxt_path', type=str, default='../data_test/class_txt_manual',
                        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=0.4, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, 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()
    print(opt)

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()

关于这段代码的操作 

运行会有一个UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb2 in position 6: invalid start byte的报错

需要进入torch.utils第58行进行修改

 将decode()改为 decode('utf-8', 'ignore')

还有第85行的decode进行修改

 修改为 decode('utf-8', 'ignore')就可以运行了