Detailed explanation of detect.py of yolov5 source code
Lines 27~46, import libraries and custom modules
import argparse
import os
import sys
from pathlib import Path
import torch
import torch.backends.cudnn as cudnn
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, time_sync
code body
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s) 事先训练完成的权重文件
# source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
source=ROOT / 'data/videos', # file/dir/URL/glob, 0 for webcam 预测时的输入数据，可以是文件/路径/URL/glob, 输入是0的话调用摄像头作为输入
data=ROOT / 'data/coco128.yaml', # dataset.yaml path 数据集文件
imgsz=(640, 640), # inference size (height, width) 预测时的放缩后图片大小(因为YOLO算法需要预先放缩图片), 两个值分别是height, widt
conf_thres=0.25, # confidence threshold 置信度，高于此值的bounding_box才会被保留
iou_thres=0.45, # NMS IOU threshold IOU阈值，高于此值的bounding_box才会被保留
max_det=1000, # maximum detections per image一张图最大检测目标个数
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu 所使用的GPU编号，如果使用CPU就写cpu
view_img=False, # show results 是否在推理时预览图片
save_txt=False, # save results to *.txt 是否将结果保存在txt文件中
save_conf=False, # save confidences in --save-txt labels 是否将结果中的置信度保存在txt文件中
save_crop=False, # save cropped prediction boxes 是否保存裁剪后的预测框
nosave=False, # do not save images/videos 是否保存预测后的图片/视频
classes=None, # filter by class: --class 0, or --class 0 2 3 过滤指定类的预测结果
agnostic_nms=False, # class-agnostic NMS 如为True,则为class-agnostic. 否则为class-specific
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name 结果保存的路径
name='exp', # save results to project/name 结果保存文件夹的命名
exist_ok=False, # existing project/name ok, do not increment True: 推理结果覆盖之前的结果 False: 推理结果新建文件夹保存,文件夹名递增
line_thickness=3, # bounding box thickness (pixels) 绘制Bounding_box的线宽度
hide_labels=False, # hide labels 隐藏标签
hide_conf=False, # hide confidences 隐藏置信度
half=False, # use FP16 half-precision inference 是否使用半精度推理（节约显存）
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)#判断是不是文件
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))#判断是不是网络流地址
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)#判断是不是调用摄像头，txt文件，网络流地址且不是文件
if is_url and is_file:
source = check_file(source) # download根据网络流下载文件
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run增量保存runs/detect/exp文件
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir根据save_txt判断exp文件中是否增加labels
# Load model
device = select_device(device)#判断加载CPU还是GPU
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)#选择模型框架，例如pytorch，加载模型
stride, names, pt = model.stride, model.names, model.pt#读取模型能检测的步长，类别名，是否为pytorch
imgsz = check_img_size(imgsz, s=stride) # check image size imgsz是640*640，满足32倍数
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # 令batch_size=1
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
seen, windows, dt = 0, [], [0.0, 0.0, 0.0]
for path, im, im0s, vid_cap, s in dataset:#im是resize后图片，im0s是原图
t1 = time_sync()
im = torch.from_numpy(im).to(device)#转成tensor给GPU torch.Size[3,640,480]
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0 归一化
if len(im.shape) == 3:
im = im[None] # expand for batch dim 扩增 torch.Size[1,3,640,480]
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)#torch.Size[1,18900,85] visualize表示是否保持推断中间特征图，augment表示是否数据增强
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)#torch.Size[1,5,6]
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
for i, det in enumerate(pred): # per image torch.Size[5,6]
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 保存路径/图片名
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 图片尺寸640*480
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh 获得原图宽高
imc = im0.copy() if save_crop else im0 # for save_crop 是否将检测框裁剪下来单独保存成图片
annotator = Annotator(im0, line_width=line_thickness, example=str(names))#原图，检测框粗细，标签名
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()#将预测图片640*480中的框映射回原图
# Print results 统计框的类别，数量
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 保存预测结果
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file 是否结果保存到txt
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 结果保存到图片上
c = int(cls) # integer class 获得类别
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')#标签和置信度格式
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:#是否要将目标框截下来保存
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
# Stream results
im0 = annotator.result()#得到画好的图片
if view_img:#是否展示图片
if 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:#是否保存图片
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}Done. ({t3 - t2:.3f}s)')
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image 统计每张图片平均时间
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_img:#如果保存了图片或txt
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}")#展示图片被保存在哪个文件夹
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
The meanings of the various parameters in the rest of the parse_opt() code are the same as before