是继续在detect.py修改，还是在ploy.py,yolo.py修改
# Run inference
model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup
# model.half().to(device) # to FP16
# model.eval()
seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
for path, im, im0s, vid_cap, s in dataset:
with dt[0]:
im = torch.from_numpy(im).to(model.device) # 将图片转换为tensor，并放到模型的设备上，pytorch模型的输入必须是tensor
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3: # 如果图片的维度为3，则添加batch维度
im = im[None] # expand for batch dim
# 在前面添加batch维度，即将图片的维度从3维转换为4维，即(3,640,640)转换为(1,3,640,640)，pytorch模型的输入必须是4维的
# Inference
with dt[1]:
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
# NMS
with dt[2]:
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
import math
# Process predictions
num_boxes = 0
max_length_per_class2 = {} # 用字典记录每个第二类锚框的最长边
num_class1_boxes_per_class2 = {} # 用字典记录每个第二类锚框中的第一类锚框数量
total_distance = 0
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, 5].unique():
n = (det[:, 5] == 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 save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(f'{txt_path}.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Calculate box statistics
if cls == 1: # Assuming class 1 represents the second category
num_boxes += 1
length = max(xyxy[2] - xyxy[0], xyxy[3] - xyxy[1])
if cls in max_length_per_class2:
max_length_per_class2[cls] = max(max_length_per_class2[cls], length)
else:
max_length_per_class2[cls] = length
center_x = (xyxy[0] + xyxy[2]) / 2
center_y = (xyxy[1] + xyxy[3]) / 2
total_distance += math.sqrt(center_x ** 2 + center_y ** 2) # Euclidean distance
elif cls == 0: # Assuming class 0 represents the first category
if cls in num_class1_boxes_per_class2:
num_class1_boxes_per_class2[cls] += 1
else:
num_class1_boxes_per_class2[cls] = 1
# Stream results
im0 = annotator.result()
if view_img:
if platform.system() == 'Linux' and p not in windows:
windows.append(p)
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release() # release previous video writer
if vid_cap: # video
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))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
# Print time (inference-only)
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
# Calculate average distance
if num_boxes > 0:
average_distance = total_distance / num_boxes
else:
average_distance = 0
# Print results
t = tuple(x.t / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
LOGGER.info(f"Number of boxes: {num_boxes}")
for cls, length in max_length_per_class2.items():
LOGGER.info(f"Maximum box length for class {int(cls)} {names[int(cls)]}: {length}")
LOGGER.info(f"Average distance between box centers: {average_distance}")
for cls, count in num_class1_boxes_per_class2.items():
LOGGER.info(f"Number of class 1 boxes in class 2 {names[int(cls) + 1]} predictions: {count}")
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)
#输出结果
image 2/2 E:\yolov5-master\VOC2012\YOLO\images\test\19.jpg: 640x608 5 paddys, 2 caves, 31.9ms
Speed: 1.5ms pre-process, 33.4ms inference, 3.5ms NMS per image at shape (1, 3, 640, 640)
Number of boxes: 2
Maximum box length for class 1 cave: 254.0
Maximum box length for class 1 cave: 530.0
Average distance between box centers: 2019.2025964486338
Number of class 1 boxes in class 2 cave predictions: 1
Number of class 1 boxes in class 2 cave predictions: 1
Number of class 1 boxes in class 2 cave predictions: 1
Number of class 1 boxes in class 2 cave predictions: 1
Number of class 1 boxes in class 2 cave predictions: 1
Results saved to runs\detect\exp248
我想要的功能是判断第一类锚框在哪个第二类锚框里，并将每个第二类锚框内的第一类锚框标号分类，并且分别计算各个第二类锚框里边各自有多少第一类锚框数量，计算每个第二类锚框的最长边，计算每一张图中两个第二类锚框之间中心点坐标的距离
将上述代码输出结果换成：
Number of class 1 boxes in class 2 cave predictions1: 2
Number of class 1 boxes in class 2 cave predictions: 3
- 这篇博客: YoLoV5学习（4）--detect.py程序（预测图片、视频、网络流）逐段讲解~中的 3.1 对source传入的东西进行额外判断 部分也许能够解决你的问题, 你可以仔细阅读以下内容或跳转源博客中阅读:
此处的source对应run函数中的source,代表图片路径；第三行代码判断是否传入为文件地址，IMG_FORMATS表示各种图片类型，VID_FORMATS表示各种视频类型；第四行代码判断是否为网络流传入；第五行代码source.isnumeric判断是否传入为数字，–source 0,数字0表示打开电脑的第一个摄像头；如果是一个网络流且是一个文件，就会进行下载操作。