import argparse
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, check_requirements, non_max_suppression, apply_classifier, scale_coords, \
xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
def detect(save_img=False):
#source:测试数据，可以是图片/视频路径，也可以是'0'(电脑自带摄像头),也可以是rtsp等视频流
#view_img是否展示预测之后的图片/视频，默认False
#save_txt预测的框坐标是否以txt文件形式保存，默认False
#imgsz网络输入图片的大小
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
# isnumeric() 方法检测字符串是否只由数字组成
#lower()大写字母转换成小写字母.startswith是否以指定字符串开头
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://'))
# Directories
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Initialize
set_logging()
#选择设备
device = select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # 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']).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, stride=stride)
# else:
save_img = True
dataset = LoadImages(source, img_size=imgsz, stride=stride)
print(dataset)
# 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]
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
#img0 = cv2.imread(path)
#path图片/视频路径
# img进行resize + pad之后的图片
# img0原size图片
# cap当读取图片时为None，读取视频时为视频源
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
# Apply NMS
"""
pred:前向传播的输出
conf_thres:置信度阈值
iou_thres:iou阈值
classes:是否只保留特定的类别
agnostic:进行nms是否也去除不同类别之间的框
经过nms之后，预测框格式：xywh-->xyxy(左上角右下角)
pred是一个列表list[torch.tensor]，长度为batch_size
每一个torch.tensor的shape为(num_boxes, 6),内容为box+conf+cls
"""
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t2 = time_synchronized()
# Apply Classifier
#添加二次分类，默认不使用
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process detections
#对每一张图片做处理
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
else:
#getattr(dataset, 'frame', 0)获取dataset中的属性值frame,不存在返回0
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
p = Path(p) # to Path
#图片保存路径
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if len(det):
# Rescale boxes from img_size to im0 size
#坐标格式为xyxy
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results
#打印检测到的类别数量
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
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 opt.save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or view_img: # Add bbox to image
#输出标签和得分值
label = f'{names[int(cls)]} {conf:.2f}'
#绘制类别和得分框信息
plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=5)
# Print time (inference + NMS)
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(str(p), im0)
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video'
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:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
print(f"Results saved to {save_dir}{s}")
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
# parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--weights', nargs='+', type=str, default='./runs/train/exp29/weights/best.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)')
#置信度输出阈值
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('--save-conf', action='store_true', help='save confidences in --save-txt labels')
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()
print(opt)
check_requirements()
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()
#清除掉权重内的opt等信息
strip_optimizer(opt.weights)
else:
detect()
