yolov5——detect.py代码【注释、详解、使用教程】
yolov5——detect.py代码【注释、详解、使用教程】
根据目前的最新版本的yolov5代码做出注释和详解以及使用教程,对了目前已经是v6,不知道你看博客的时候是什么版本呢,总的来说越来越先进越来越完善,越来越适合无脑啊哈哈哈,没你说哈IIII
1. 函数parse_opt()
def parse_opt():
"""
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
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
"""
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for 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')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1
print_args(FILE.stem, opt)
return opt
2. 函数main()
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
3. 函数run()
3.1 run函数——传入参数
def run(weights=ROOT / 'yolov5s.pt',
source=ROOT / 'data/images',
data=ROOT / 'data/coco128.yaml',
imgsz=(640, 640),
conf_thres=0.25,
iou_thres=0.45,
max_det=1000,
device='',
view_img=False,
save_txt=False,
save_conf=False,
save_crop=False,
nosave=False,
classes=None,
agnostic_nms=False,
augment=False,
visualize=False,
update=False,
project=ROOT / 'runs/detect',
name='exp',
exist_ok=False,
line_thickness=3,
hide_labels=False,
hide_conf=False,
half=False,
dnn=False,
):
3.2 run函数——初始化配置
source = str(source)
save_img = not nosave and not source.endswith('.txt')
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)
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride)
half &= (pt or jit or onnx or engine) and device.type != 'cpu'
if pt or jit:
model.model.half() if half else model.model.float()
elif engine and model.trt_fp16_input != half:
LOGGER.info('model ' + (
'requires' if model.trt_fp16_input else 'incompatible with') + ' --half. Adjusting automatically.')
half = model.trt_fp16_input
3.3 run函数——加载数据
if webcam:
view_img = check_imshow()
cudnn.benchmark = True
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1
vid_path, vid_writer = [None] * bs, [None] * bs
3.4 run函数——输入预测
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float()
im /= 255
if len(im.shape) == 3:
im = im[None]
t2 = time_sync()
dt[0] += t2 - t1
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
"""
pred.shape=(1, num_boxes, 5+num_class)
h,w为传入网络图片的长和宽,注意dataset在检测时使用了矩形推理,所以这里h不一定等于w
num_boxes = h/32 * w/32 + h/16 * w/16 + h/8 * w/8
pred[..., 0:4]为预测框坐标=预测框坐标为xywh(中心点+宽长)格式
pred[..., 4]为objectness置信度
pred[..., 5:-1]为分类结果
"""
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
3.5 run函数——NMS
"""
pred: 网络的输出结果
conf_thres:置信度阈值
ou_thres:iou阈值
classes: 是否只保留特定的类别
agnostic_nms: 进行nms是否也去除不同类别之间的框
max-det: 保留的最大检测框数量
---NMS, 预测框格式: xywh(中心点+长宽)-->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, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
3.6 run函数——保存打印
for i, det in enumerate(pred):
seen += 1
if webcam:
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)
save_path = str(save_dir / p.name)
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')
s += '%gx%g ' % im.shape[2:]
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]
imc = im0.copy() if save_crop else im0
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum()
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "
for *xyxy, conf, cls in reversed(det):
if save_txt:
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
line = (cls, *xywh, conf) if save_conf else (cls, *xywh)
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img:
c = int(cls)
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)
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else:
if vid_path[i] != save_path:
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release()
if vid_cap:
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:
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4'))
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
4. detect.py全部注释
"""
Run inference on images, videos, directories, streams, etc.
Usage - sources:
$ python path/to/detect.py --weights yolov5s.pt --source 0 # webcam # 直播软件/电脑摄像头
img.jpg # image
vid.mp4 # video
path/ # directory
path/*.jpg # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
Usage - formats:
$ python path/to/detect.py --weights yolov5s.pt # PyTorch
yolov5s.torchscript # TorchScript
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
yolov5s.xml # OpenVINO
yolov5s.engine # TensorRT
yolov5s.mlmodel # CoreML (MacOS-only)
yolov5s_saved_model # TensorFlow SavedModel
yolov5s.pb # TensorFlow GraphDef
yolov5s.tflite # TensorFlow Lite
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
"""
import argparse
import os
import sys
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT))
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))
from models.common import DetectMultiBackend
from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
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
@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt',
source=ROOT / 'data/images',
data=ROOT / 'data/coco128.yaml',
imgsz=(640, 640),
conf_thres=0.25,
iou_thres=0.45,
max_det=1000,
device='',
view_img=False,
save_txt=False,
save_conf=False,
save_crop=False,
nosave=False,
classes=None,
agnostic_nms=False,
augment=False,
visualize=False,
update=False,
project=ROOT / 'runs/detect',
name='exp',
exist_ok=False,
line_thickness=3,
hide_labels=False,
hide_conf=False,
half=False,
dnn=False,
):
source = str(source)
save_img = not nosave and not source.endswith('.txt')
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)
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride)
half &= (pt or jit or onnx or engine) and device.type != 'cpu'
if pt or jit:
model.model.half() if half else model.model.float()
elif engine and model.trt_fp16_input != half:
LOGGER.info('model ' + (
'requires' if model.trt_fp16_input else 'incompatible with') + ' --half. Adjusting automatically.')
half = model.trt_fp16_input
if webcam:
view_img = check_imshow()
cudnn.benchmark = True
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1
vid_path, vid_writer = [None] * bs, [None] * bs
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float()
im /= 255
if len(im.shape) == 3:
im = im[None]
t2 = time_sync()
dt[0] += t2 - t1
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
"""
pred.shape=(1, num_boxes, 5+num_class)
h,w为传入网络图片的长和宽,注意dataset在检测时使用了矩形推理,所以这里h不一定等于w
num_boxes = h/32 * w/32 + h/16 * w/16 + h/8 * w/8
pred[..., 0:4]为预测框坐标=预测框坐标为xywh(中心点+宽长)格式
pred[..., 4]为objectness置信度
pred[..., 5:-1]为分类结果
"""
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
"""
pred: 网络的输出结果
conf_thres:置信度阈值
ou_thres:iou阈值
classes: 是否只保留特定的类别
agnostic_nms: 进行nms是否也去除不同类别之间的框
max-det: 保留的最大检测框数量
---NMS, 预测框格式: xywh(中心点+长宽)-->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, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() - t3
for i, det in enumerate(pred):
seen += 1
if webcam:
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)
save_path = str(save_dir / p.name)
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')
s += '%gx%g ' % im.shape[2:]
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]
imc = im0.copy() if save_crop else im0
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
if len(det):
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum()
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "
for *xyxy, conf, cls in reversed(det):
if save_txt:
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
line = (cls, *xywh, conf) if save_conf else (cls, *xywh)
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img:
c = int(cls)
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)
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else:
if vid_path[i] != save_path:
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release()
if vid_cap:
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:
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4'))
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
t = tuple(x / seen * 1E3 for x in dt)
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)
def parse_opt():
"""
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
"""
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for 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')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1
print_args(FILE.stem, opt)
return opt
def main(opt):
check_requirements(exclude=('tensorboard', 'thop'))
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)
5. 使用教程
python detect.py --weights ./weights/yolov5s.pt --source ./data/test_images/ --classes 5 --save-txt --save-crop
crop文件夹下的文件 labels下面的文件
|