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, check_imshow, 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, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
# 是否保存图片的判断(bool类型),默认为保存图片,不保存图片可以在执行程序中输入 - -nosave,或者你检测的对象是一个网络视频流的地址,其中视频流地址保存在一个文件类型为txt的文档里
save_img = not opt.nosave and not source.endswith('.txt') # save inference images
# 摄像头检测
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# Directories 保存检测结果地址
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() # 打印日志信息
device = select_device(opt.device)
# 如果设备为gpu,使用FP16
half = device.type != 'cpu' # half precision only supported on CUDA 通过降低少许检测精度提高检测速度的判断,
# Load model
# 加载Float32模型,确保用户设定的输入图片分辨率能整除32
model = attempt_load(weights, map_location=device) # load FP32 model
# yolov5也用了FPN里面的一个思路,将卷积神经网络中最后三层通过上采样的方式进行了一个堆叠的,要求图片的分辨率为32的一个整数倍。
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 设置第二级分类,默认不使用
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 通过不同的输入源来设置不同的数据加载方式
# vid_path, vid_writer = None, None
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)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Get names and colors
# 获取类别名字字符列表
names = model.module.names if hasattr(model, 'module') else model.names
# 设置画框的颜色(RGB值的列表)
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()))) # 测试一次推理,测试程序是否正常
t0 = time.time()
"""
path 图片/视频路径
img 进行resize和padding之后的图片
im0s 原size图片
vid_cap 当读的是图片为None,读的是视频为视频源
"""
for path, img, im0s, vid_cap in dataset:
img = torch.from_numpy(img).to(device) # 把图片转成tensor格式,并指派到设备上
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) # 增加一个维度
# Inference 前向传播
t1 = time_synchronized()
pred = model(img, augment=opt.augment)[0]
# Apply NMS 后处理
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t2 = time_synchronized()
# Apply Classifier 二级分类,默认不使用
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, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
else:
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
p = Path(p) # to Path
# 设置保存图片/视频的路径
save_path = str(save_dir / p.name) # img.jpg
# 设置保存框坐标txt文件的路径
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
# 设置打印信息
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 调整预测框的坐标,还原回原图的坐标
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 保存预测结果
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
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 是否展示
if view_img:
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 != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.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 += '.mp4'
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), 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__':
#建立参数解析对象parser
parser = argparse.ArgumentParser()
# 添加属性
# nargs -应该读取的命令行参数个数。 * 表示0或多个参数; + 表示1或多个参数
# action - 命令行遇到参数时的动作。action = ‘store_true’,只要运行时该变量有传参就把该变量设为True
parser.add_argument('--weights', nargs='+', type=str, default='./weights/yolov5m.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images/bus.jpg', 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('--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')# 默认False
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')# 框坐标
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')# 框置信度
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')# 进行NMS是否也去除不同类别之间的框,默认False
parser.add_argument('--augment', action='store_true', help='augmented inference')# 推理的时候进行多尺度,翻转等增强操纵
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')# 有没有,没有就创建
# 采用parser对象的parse_args函数获取解析的参数
opt = parser.parse_args()
print(opt)
# 查看requirements.txt里的相关安装包是否安装在执行检测的python环境下
# check_requirements(exclude=('pycocotools', 'thop'))
with torch.no_grad(): # 一个上下文管理器,被该语句包含起来的部分不会计算梯度
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) # 去除pt文件中的优化器等信息
else:
detect()
【无标题】
最新推荐文章于 2024-07-13 21:34:41 发布