import argparse import time from pathlib import Path from PIL import Image import numpy as np import cv2 import torch import torch.backends.cudnn as cudnn from numpy import random from super_image import EdsrModel, ImageLoader 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 def detect(save_img=False): source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, not opt.no_trace save_img = not opt.nosave and not source.endswith('.txt') # save inference images webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( ('rtsp://', 'rtmp://', 'http://', 'https://')) # 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) half = device.type != 'cpu' # half precision only supported on CUDA # Load YOLOv7 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 if trace: model = TracedModel(model, device, opt.img_size) if half: model.half() # to FP16 # Set Dataloader vid_path, vid_writer = None, None 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) else: dataset = LoadImages(source, img_size=imgsz, stride=stride) # Get names and colors names = model.module.names if hasattr(model, 'module') else model.names colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] # Run inference if device.type != 'cpu': model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once old_img_w = old_img_h = imgsz old_img_b = 1 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) # Warmup if device.type != 'cpu' and (old_img_b != img.shape[0] or old_img_h != img.shape[2] or old_img_w != img.shape[3]): old_img_b = img.shape[0] old_img_h = img.shape[2] old_img_w = img.shape[3] for i in range(3): model(img, augment=opt.augment)[0] # Inference t1 = time_synchronized() with torch.no_grad(): # Calculating gradients would cause a GPU memory leak pred = model(img, augment=opt.augment)[0] t2 = time_synchronized() # Apply NMS pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) t3 = time_synchronized() # Process detections for i, det in enumerate(pred): # detections per image if webcam: # batch_size >= 1 p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count else: 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 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() # Find box with maximum confidence score max_conf_idx = det[:, 4].argmax().item() xyxy_max_conf = det[max_conf_idx][:4] # coordinates of max confidence bbox # Crop the image using max confidence bbox x1, y1, x2, y2 = map(int, xyxy_max_conf) cropped_img = im0[y1:y2, x1:x2] # Convert the cropped image from BGR to RGB format (OpenCV uses BGR by default) cropped_img_rgb = cv2.cvtColor(cropped_img, cv2.COLOR_BGR2RGB) # Convert the NumPy array (H, W, C) to a PyTorch tensor (C, H, W) and normalize the pixel values cropped_img_tensor = torch.from_numpy(cropped_img_rgb).float().permute(2, 0, 1) / 255.0 # Add batch dimension since the model expects batches of images inputs = cropped_img_tensor.unsqueeze(0) # Load EDSR model with scale 2 edsr_model = EdsrModel.from_pretrained('eugenesiow/drln-bam', scale=2) # Perform super-resolution on the cropped image preds = edsr_model(inputs) # Convert the result back to a NumPy array and save it upscaled_img = preds.squeeze(0).cpu().detach().numpy().transpose(1, 2, 0) # (C, H, W) -> (H, W, C) # Since the output of the model is normalized, we rescale the values back to 0-255 upscaled_img = np.clip(upscaled_img * 255.0, 0, 255).astype(np.uint8) # Convert the image back to BGR for saving (since OpenCV saves in BGR format) upscaled_img_bgr = cv2.cvtColor(upscaled_img, cv2.COLOR_RGB2BGR) # Save the final upscaled image # Save the upscaled image upscaled_img_save_path = save_dir / f"{p.stem}_upscaled.jpg" cv2.imwrite(str(upscaled_img_save_path), upscaled_img_bgr) # Save cropped image# cropped_img_save_path = save_dir / f"{p.stem}_cropped.jpg" cv2.imwrite(str(cropped_img_save_path), cropped_img) # Save upscaled image # upscaled_img_save_path = save_dir / f"{p.stem}_upscaled.jpg" # cv2.imwrite(str(upscaled_img_save_path), upscaled_img) # Display both the cropped and upscaled images if view_img: cv2.imshow("Cropped Image", cropped_img) # Show cropped image cv2.imshow("Upscaled Image", upscaled_img) # Show upscaled image cv2.waitKey(1) # Print time (inference + NMS) print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS') print(f'Done. ({time.time() - t0:.3f}s)') if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default='yolov7.pt', help='model.pt path(s)') parser.add_argument('--source', type=str, default='inference/images', 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('--no-trace', action='store_true', help='don`t trace model') opt = parser.parse_args() print(opt) #check_requirements(exclude=('pycocotools', 'thop')) with torch.no_grad(): if opt.update: # update all models (to fix SourceChangeWarning) for opt.weights in ['yolov7.pt']: detect() strip_optimizer(opt.weights) else: detect()