yYOLOv5 val.py重写

重写 YOLOv5 的 val.py 可以通过以下步骤完成：

1. 导入必要的库和模块：

import argparse
import os
import time

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

from models.experimental import attempt_load
from utils.datasets import LoadImages
from utils.general import check_img_size, non_max_suppression, scale_coords
from utils.plots import plot_one_box
from utils.torch_utils import select_device, time_synchronized

2. 设置命令行参数并解析：

parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images', help='source')  # file/folder, 0 for webcam
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('--max-det', type=int, default=1000, help='maximum number of detections per image')
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('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
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')
parser.add_argument('--project', default='runs/detect', help='save results to project/name')
parser.add_argument('--name', default='exp', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
opt = parser.parse_args()

3. 加载模型：

device = select_device(opt.device)
half = device.type != 'cpu'  # half precision only supported on CUDA

# Load model
model = attempt_load(opt.weights, map_location=device)  # load FP32 model
if half:
    model.half()  # to FP16

# Set Dataloader
vid_path, vid_writer = None, None
if opt.source.endswith('.txt'):
    with open(opt.source, 'r') as f:
        dataset = [x.strip() for x in f.readlines()]
elif opt.source.endswith(('mp4', 'avi', 'mov')):
    vid_path = opt.source
    if not os.path.exists(opt.source):
        raise FileNotFoundError(f'File not found: {opt.source}')
    dataset = [opt.source]
else:
    dataset = LoadImages(opt.source, img_size=opt.img_size)

# 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 names]

4. 设置图片大小和推理模式：

imgsz = check_img_size(opt.img_size, s=model.stride.max())  # check img_size
if opt.device.type != 'cpu':
    cudnn.benchmark = True  # set True to speed up constant image size inference

5. 对每张图片进行推理：

for path, img, im0s, vid_cap in dataset:
    t1 = time_synchronized()

    # Get detections
    img = torch.from_numpy(img).to(device)
    if img.ndimension() == 3:
        img = img.unsqueeze(0)
    pred = model(img, augment=opt.augment)[0]

    # Apply NMS
    pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms, max_det=opt.max_det)

    t2 = time_synchronized()

    # Process detections
    for i, det in enumerate(pred):  # detections per image
        if webcam:
            p, s, im0 = path[i], f'{i}: ', im0s[i].copy()
        else:
            p, s, im0 = path, '', im0s

        save_path = str(Path(opt.project) / Path(p).name)
        txt_path = str(Path(opt.project) / Path(p).stem) + ('' if dataset.mode == 'image' else f'_{dataset.count}.txt')  # txt filename

        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 += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

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

                if opt.save_crop or opt.save_conf:  # Save cropped prediction boxes
                    save_one_box(xyxy, im0, file=save_path, BGR=True)

                if opt.view_img:  # Add bbox to image
                    label = f'{names[int(cls)]} {conf:.2f}'
                    plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)

        # Print time (inference + NMS)
        print(f'{s}Done. ({t2 - t1:.3f}s)')

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

6. 保存结果：

        # Save results (image with detections)
        if not opt.nosave:
            if dataset.mode == 'images':
                cv2.imwrite(save_path, im0)
            else:
                if vid_path != vid_writer:  # new video
                    vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), vid_cap.get(cv2.CAP_PROP_FPS), (round(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)), round(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))))
                vid_writer.write(im0)

以上就是重写 YOLOv5 的 val.py 的主要步骤，可以根据实际需求进行调整和修改。