import gradio as gr import os #os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt") os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt") os.system("wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt") os.system("wget https://github.com/CAIC-AD/YOLOPv2/releases/download/V0.0.1/yolopv2.pt") import argparse import time from pathlib import Path import cv2 import torch import torch.backends.cudnn as cudnn from numpy import random 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 from utils.plots import plot_one_box from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel from utils.functions import \ time_synchronized,select_device, increment_path,\ scale_coords,xyxy2xywh,non_max_suppression,split_for_trace_model,\ driving_area_mask,lane_line_mask,plot_one_box,show_seg_result,\ AverageMeter,\ LoadImages from PIL import Image def detect(img,model): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=model+".pt", help='model.pt path(s)') parser.add_argument('--source', type=str, default='Inference/', help='source') # file/folder, 0 for webcam 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('--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('--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('--trace', action='store_true', help='trace model') opt = parser.parse_args() img.save("Inference/test.jpg") source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, opt.trace save_img = True # save inference images #webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( #('rtsp://', 'rtmp://', 'http://', 'https://')) #print(webcam) # Directories save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir # Initialize set_logging() device = select_device(opt.device) print(device) half = device.type != 'cpu' # half precision only supported on CUDA # Load model inf_time = AverageMeter() waste_time = AverageMeter() nms_time = AverageMeter() # Load model #model = attempt_load(weights, map_location=device) # load FP32 model #stride = int(model.stride.max()) # model stride #imgsz = check_img_size(imgsz, s=stride) # check img_size print(weights) stride =32 model = torch.jit.load(weights,map_location=device) model.eval() # Set Dataloader vid_path, vid_writer = None, None dataset = LoadImages(source, img_size=imgsz, stride=stride) # Run inference if device.type != 'cpu': model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once 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() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 if img.ndimension() == 3: img = img.unsqueeze(0) # Inference t1 = time_synchronized() [pred,anchor_grid],seg,ll= model(img) t2 = time_synchronized() # waste time: the incompatibility of torch.jit.trace causes extra time consumption in demo version # but this problem will not appear in offical version tw1 = time_synchronized() pred = split_for_trace_model(pred,anchor_grid) tw2 = time_synchronized() # Apply NMS t3 = time_synchronized() pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) t4 = time_synchronized() da_seg_mask = driving_area_mask(seg) ll_seg_mask = lane_line_mask(ll) # Process detections for i, det in enumerate(pred): # detections per image p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0) p = Path(p) # to Path save_path = str(save_dir / p.name) # img.jpg txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt s += '%gx%g ' % img.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh if len(det): # Rescale boxes from img_size to im0 size det[:, :4] = scale_coords(img.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): 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 opt.save_conf else (cls, *xywh) # label format with open(txt_path + '.txt', 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') if save_img : # Add bbox to image plot_one_box(xyxy, im0, line_thickness=3) # Print time (inference) print(f'{s}Done. ({t2 - t1:.3f}s)') show_seg_result(im0, (da_seg_mask,ll_seg_mask), is_demo=True) # Save results (image with detections) if save_img: if dataset.mode == 'image': cv2.imwrite(save_path, im0) print(f" The image with the result is saved in: {save_path}") else: # 'video' or 'stream' if vid_path != save_path: # new video vid_path = save_path if isinstance(vid_writer, cv2.VideoWriter): vid_writer.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)) w,h = im0.shape[1], im0.shape[0] else: # stream fps, w, h = 30, im0.shape[1], im0.shape[0] save_path += '.mp4' vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer.write(im0) inf_time.update(t2-t1,img.size(0)) nms_time.update(t4-t3,img.size(0)) waste_time.update(tw2-tw1,img.size(0)) print('inf : (%.4fs/frame) nms : (%.4fs/frame)' % (inf_time.avg,nms_time.avg)) print(f'Done. ({time.time() - t0:.3f}s)') return Image.fromarray(im0[:,:,::-1]) gr.Interface(detect,[gr.Image(type="pil"),gr.Dropdown(choices=["yolopv2"])], gr.Image(type="pil"),title="Yolopv2",examples=[["horses.jpeg", "yolopv2"]],description="demo for WongKinYiu/yolov7 Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors").launch()