# 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))