需求
把一部短剧中的人物都截图出来。
安装
git clone https://github.com/ultralytics/yolov5 # clone
cd yolov5
pip install -r requirements.txt # install
训练
打开yolov5目录下的README.zh-CN.md，根据提示中的训练命令进行训练。
推理
yolov5有自带的detect.py根据不同的参数可以推理生成不同的结果。
但是，我们想把短剧中的人物截图出来，自带的脚本就不行了。
而且只是截图还不行，一个视频每秒最少25帧，如果每帧都截，数据量太大。我们还需要指定每秒只截取几帧，那怎么写？
直接上代码。
import argparse
import os
import platform
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, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh)
from utils.plots import Annotator, colors, save_one_box
from utils.torch_utils import select_device, smart_inference_mode
@smart_inference_mode()
def run(
weights=ROOT / 'yolov5s.pt', # model path or triton URL
source=ROOT / 'data/images', # file/dir/URL/glob/screen/0(webcam)
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=True, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
vid_stride=1, # video frame-rate stride
sample_fps=1.0, # 新增参数：每秒采样的帧数
):
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)
is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
if webcam:
view_img = check_imshow()
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# 新增：视频采样相关变量
frame_count = 0
prev_time = 0
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
seen, windows, dt = 0, [], (Profile(), Profile(), Profile())
for path, im, im0s, vid_cap, s in dataset:
# 新增：视频采样逻辑
if dataset.mode == 'video':
if vid_cap:
fps = vid_cap.get(cv2.CAP_PROP_FPS)
current_time = frame_count / fps
# 计算需要跳过的帧数
frames_to_skip = max(1, int(fps / sample_fps))
# 只处理指定间隔的帧
if frame_count % frames_to_skip != 0:
frame_count += 1
continue
frame_count += 1
# 打印采样信息
if frame_count % 100 == 0:
LOGGER.info(f"视频采样: FPS={fps}, 目标采样率={sample_fps}fps, 实际采样率={1/(current_time-prev_time):.2f}fps")
prev_time = current_time
with dt[0]:
im = torch.from_numpy(im).to(model.device)
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:
im = im[None] # expand for batch dim
# 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)
# Process predictions
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: # 保存裁剪的图像
# 获取检测框坐标
x1, y1, x2, y2 = map(int, xyxy)
# 裁剪图像
cropped_img = imc[y1:y2, x1:x2]
if cropped_img.size == 0:
continue
# 保存裁剪的图像
crop_dir = save_dir / 'crops' / names[c]
crop_dir.mkdir(parents=True, exist_ok=True)
# 新增：在文件名中包含时间信息
if dataset.mode == 'video':
time_str = f"{current_time:.2f}s" if 'current_time' in locals() else f"frame{frame}"
crop_path = crop_dir / f"{p.stem}_{time_str}_{x1}_{y1}_{x2}_{y2}.jpg"
else:
crop_path = crop_dir / f"{p.stem}_{x1}_{y1}_{x2}_{y2}.jpg"
cv2.imwrite(str(crop_path), cropped_img)
LOGGER.info(f"裁剪的对象已保存至 {crop_path}")
# 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 * 1000:.1f}ms")
# Print results
t = tuple(x.t / seen * 1000 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)
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)
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL')
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
parser.add_argument('--max-det', type=int, default=1000, help='maximum 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='show 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: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default=ROOT / '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')
parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
parser.add_argument('--sample-fps', type=float, default=1.0, help='每秒采样的帧数') # 新增参数
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(vars(opt))
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
截图命令
截取小猫
python detect.py --classes=15 --source="data/src/demoCat" --project="runs/demoCatResult" --save-txt --save-csv
截取视频中的所有门类
python detect.py --source="data/src/mp4/1.mp4" --project="runs/mp4Result" --save-txt --save-csv
把目录中的小猫图片中的小猫截取出来
python detect_with_crop.py --source data/src/demoCat --weights yolov5s.pt --project runs/demoCatResult --save-crop
把短剧视频中的人物都截取出来
python detect_with_crop2.py --classes 0 --source data/src/mp4/2.mp4 --weights yolov5s.pt --project runs/mp4Result --save-crop --sample-fps 2.0
说明
--classes 指定目标匹配的门类，0代表人，15代表猫；
--save-txt 会把匹配的结果写到text里，text里的内容有五列```<类别编号> <中心点 x> <中心点 y> <宽度> <高度> <置信度>```
--weights 指定已经训练好的模型;
--save-crop 上述自定义脚本的自有命令，用于把源中的目标截图出来
--sample-fps 指定目标识别的帧率，2.0 表示每秒只选取两帧识别
其他关键字和参数说明
weights: 训练的权重路径,可以使用自己训练的权重,也可以使用官网提供的权重
默认官网的权重yolov5s.pt(yolov5n.pt/yolov5s.pt/yolov5m.pt/yolov5l.pt/yolov5x.pt/区别在于网络的宽度和深度以此增加)
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, 默认data/images
data: 配置数据文件路径, 包括image/label/classes等信息, 训练自己的文件, 需要作相应更改, 可以不用管
如果设置了只显示个别类别即使用了--classes = 0 或二者1, 2, 3等, 则需要设置该文件，数字和类别相对应才能只检测某一个类
imgsz: 网络输入图片大小, 默认的大小是640
conf-thres: 置信度阈值， 默认为0.25
iou-thres: 做nms的iou阈值, 默认为0.45
max-det: 保留的最大检测框数量, 每张图片中检测目标的个数最多为1000类
device: 设置设备CPU/CUDA, 可以不用设置
view-img: 是否展示预测之后的图片/视频, 默认False, --view-img 电脑界面出现图片或者视频检测结果
save-txt: 是否将预测的框坐标以txt文件形式保存, 默认False, 使用--save-txt 在路径runs/detect/exp*/labels/*.txt下生成每张图片预测的txt文件
save-conf: 是否将置信度conf也保存到txt中, 默认False
save-crop: 是否保存裁剪预测框图片, 默认为False, 使用--save-crop 在runs/detect/exp*/crop/剪切类别文件夹/ 路径下会保存每个接下来的目标
nosave: 不保存图片、视频, 要保存图片，不设置--nosave 在runs/detect/exp*/会出现预测的结果
classes: 设置只保留某一部分类别, 形如0或者0 2 3, 使用--classes = n, 则在路径runs/detect/exp*/下保存的图片为n所对应的类别, 此时需要设置data
agnostic-nms: 进行NMS去除不同类别之间的框, 默认False
augment: TTA测试时增强/多尺度预测, 可以提分
visualize: 是否可视化网络层输出特征
update: 如果为True,则对所有模型进行strip_optimizer操作,去除pt文件中的优化器等信息,默认为False
project: 保存测试日志的文件夹路径
name: 保存测试日志文件夹的名字, 所以最终是保存在project/name中
exist_ok: 是否重新创建日志文件, False时重新创建文件
line-thickness: 画框的线条粗细
hide-labels: 可视化时隐藏预测类别
hide-conf: 可视化时隐藏置信度
half: 是否使用F16精度推理, 半进度提高检测速度
dnn: 用OpenCV DNN预测
最终结果
以上面最后一条命令举例，在“runs/mp4Result”目录中生成了在源视频上打标之后的结果。在runs/mp4Result/crops/person内生成了从视频中截取的人物图片。
参考文献
转载请注明来源：https://www.cnblogs.com/bugutian/
浙公网安备 33010602011771号