316 lines
16 KiB
Python
316 lines
16 KiB
Python
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
|
|
|
import argparse
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
import time
|
|
|
|
import torch
|
|
import torch.backends.cudnn as cudnn
|
|
import aiohttp
|
|
import asyncio
|
|
import requests
|
|
|
|
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, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
|
|
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
|
|
|
|
|
|
|
|
# 异步获取数据的函数
|
|
async def fetch(session, url, data): # 修改为异步函数
|
|
async with session.post(url, json=data) as response:
|
|
return await response.text()
|
|
|
|
@torch.no_grad()
|
|
async def run_async( # 修改函数定义为异步
|
|
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,
|
|
skip_frames=5, # Number of frames to skip between processing
|
|
):
|
|
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()
|
|
cudnn.benchmark = True # set True to speed up constant image size inference
|
|
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
|
|
bs = len(dataset) # batch_size
|
|
else:
|
|
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
|
|
bs = 1 # batch_size
|
|
vid_path, vid_writer = [None] * bs, [None] * bs
|
|
|
|
frame_index = 0 # Initialize frame index
|
|
|
|
# Run inference
|
|
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup
|
|
dt, seen = [0.0, 0.0, 0.0], 0
|
|
async with aiohttp.ClientSession() as session: # 使用aiohttp的会话
|
|
for path, im, im0s, vid_cap, s in dataset:
|
|
|
|
# 跳帧
|
|
if frame_index % (skip_frames + 1) != 0:
|
|
frame_index += 1
|
|
continue # Skip this frame
|
|
frame_index += 1 # Increment frame index
|
|
|
|
t1 = time_sync()
|
|
im = torch.from_numpy(im).to(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
|
|
t2 = time_sync()
|
|
dt[0] += t2 - t1
|
|
|
|
# Inference
|
|
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
|
|
pred = model(im, augment=augment, visualize=visualize)
|
|
t3 = time_sync()
|
|
dt[1] += t3 - t2
|
|
|
|
# NMS
|
|
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
|
|
dt[2] += time_sync() - t3
|
|
|
|
# Second-stage classifier (optional)
|
|
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
|
|
|
|
# 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_coords(im.shape[2:], det[:, :4], im0.shape).round()
|
|
|
|
# Print results
|
|
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):
|
|
url = 'http://127.0.0.1:7861/chat/knowledge_base_chat'
|
|
headers = {
|
|
'Content-Type': 'application/json'
|
|
}
|
|
# 未戴安全帽
|
|
if int(cls) == 2:
|
|
if conf > 0.5: # 只有当置信度大于0.5时才处理
|
|
data = {
|
|
"query": "作业现场人员未佩戴安全帽是几级违规行为？具体违反了哪些条款？条款内容是什么？",
|
|
"knowledge_base_name": "violation",
|
|
"top_k": 2,
|
|
"score_threshold": 1.3,
|
|
"history": [],
|
|
"stream": False,
|
|
"model_name": "chatglm3-6b",
|
|
"temperature": 0.01,
|
|
"max_tokens": 4098,
|
|
"prompt_name": "default"
|
|
}
|
|
# time_start = time.time()
|
|
response = await fetch(session, 'http://127.0.0.1:7861/chat/knowledge_base_chat', data) # 修改为异步调用
|
|
# time_end = time.time()
|
|
#
|
|
# time_c = time_end - time_start # 运行所花时间
|
|
# print('time cost', time_c, 's')
|
|
print('---------------API called, response:', response)
|
|
# 未戴安全带
|
|
elif int(cls) == 4:
|
|
if conf > 0.5: # 只有当置信度大于0.5时才处理
|
|
data = {
|
|
"query": "高处作业未佩戴安全带是几级违规行为？具体违反了哪些条款？条款内容是什么？",
|
|
"knowledge_base_name": "violation",
|
|
"top_k": 2,
|
|
"score_threshold": 1.3,
|
|
"history": [],
|
|
"stream": False,
|
|
"model_name": "chatglm3-6b",
|
|
"temperature": 0.01,
|
|
"max_tokens": 4098,
|
|
"prompt_name": "default"
|
|
}
|
|
response = requests.post(url, headers=headers,json=data)
|
|
print('---------------API called, response:', response)
|
|
# 跨越围栏
|
|
elif int(cls) == 5:
|
|
if conf > 0.5: # 只有当置信度大于0.5时才处理
|
|
data = {
|
|
"query": "作业现场人员跨越围栏是几级违规行为？具体违反了哪些条款？条款内容是什么？",
|
|
"knowledge_base_name": "violation",
|
|
"top_k": 2,
|
|
"score_threshold": 1.3,
|
|
"history": [],
|
|
"stream": False,
|
|
"model_name": "chatglm3-6b",
|
|
"temperature": 0.01,
|
|
"max_tokens": 4098,
|
|
"prompt_name": "default"
|
|
}
|
|
response = requests.post(url, headers=headers,json=data)
|
|
print('---------------API called, response:', response)
|
|
|
|
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:
|
|
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
|
|
|
|
# Stream results
|
|
im0 = annotator.result()
|
|
if view_img:
|
|
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
|
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}Done. ({t3 - t2:.3f}s)')
|
|
|
|
# Print results
|
|
t = tuple(x / seen * 1E3 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) # update model (to fix SourceChangeWarning)
|
|
|
|
|
|
def parse_opt():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--weights', nargs='+', type=str, default='weights/best.pt', help='model path(s)')
|
|
# parser.add_argument('--source', type=str, default='data/images/895.jpg', help='file/dir/URL/glob, 0 for webcam')
|
|
parser.add_argument('--source', type=str, default='data/video/nohat.mp4', help='file/dir/URL/glob, 0 for webcam')
|
|
# parser.add_argument('--source', type=str, default='0', help='file/dir/URL/glob, 0 for webcam')
|
|
parser.add_argument('--data', type=str, default='data/safe_det.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', default=True, 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 # expand
|
|
print_args(vars(opt))
|
|
return opt
|
|
|
|
|
|
async def main_async(opt): # 修改为异步主函数
|
|
check_requirements(exclude=('tensorboard', 'thop'))
|
|
await run_async(**vars(opt)) # 使用await调用异步函数
|
|
|
|
|
|
if __name__ == "__main__":
|
|
opt = parse_opt()
|
|
# asyncio.run(main_async(opt)) # 使用asyncio.run启动异步任务
|
|
loop = asyncio.get_event_loop()
|
|
loop.run_until_complete(main_async(opt))
|