import argparse
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
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, save_one_box
from utils.plots import colors, plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
def my_lodelmodel():
parser = argparse.ArgumentParser()
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt',
help='model.pt path(s)')
opt = parser.parse_args()
device = select_device(opt.device)
'''
打包为exe 时候 这个select——device可能会出错，所以替换为 # device ='cuda:0'
'''
print("device", device)
weights = opt.weights
model = attempt_load(weights, map_location=device)
return model
@torch.no_grad()
def detect(opt, my_model, source_open):
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
save_img = not opt.nosave and not source.endswith('.txt')
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
label = 'debug'
save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)
set_logging()
device = select_device(opt.device)
half = opt.half and device.type != 'cpu'
model = my_model
stride = int(model.stride.max())
imgsz = check_img_size(imgsz, s=stride)
names = model.module.names if hasattr(model, 'module') else model.names
if half:
model.half()
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2)
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
vid_path, vid_writer = None, None
source = source_open
if webcam:
view_img = check_imshow()
cudnn.benchmark = True
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))
t0 = time.time()
for path, img, im0s, vid_cap in dataset:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float()
img /= 255.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
t1 = time_synchronized()
pred = model(img, augment=opt.augment)[0]
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms,
max_det=opt.max_det)
t2 = time_synchronized()
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
for i, det in enumerate(pred):
if webcam:
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
else:
p, s, 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 ' % img.shape[2:]
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]
imc = im0.copy() if opt.save_crop else im0
if len(det):
det[:, :4] = scale_coords(img.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 opt.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 opt.save_crop or view_img:
c = int(cls)
label = None if opt.hide_labels else (names[c] if opt.hide_conf else f'{names[c]} {conf:.2f}')
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
print(f'Done. ({time.time() - t0:.3f}s)')
return im0,label
def main_detect(my_model,source_open):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images', help='source')
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('--max-det', type=int, default=1000, help='maximum number of 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='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('--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: --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')
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')
opt = parser.parse_args()
print(opt)
im0, label = detect(opt, my_model, source_open)
print("detect")
return im0, label
|
wechat
alipay
