data_parser.set_defaults(valid='data/binary_sst/val.csv', test='data/binary_sst/test.csv') args = parser.parse_args() if args.seed is not -1: torch.manual_seed(args.seed) torch.cuda.manual_seed(args.seed) train_data, val_data, test_data = data_config.apply(args) ntokens = args.data_size model = model.RNNFeaturizer(args.model, ntokens, args.emsize, args.nhid, args.nlayers, 0.0, args.all_layers).cuda() if args.fp16: model.half() # load char embedding and recurrent encoder for featurization with open(args.load_model, 'rb') as f: sd = torch.load(f) if 'encoder' in sd: sd = sd['encoder'] try: model.load_state_dict(sd) except: # if state dict has weight normalized parameters apply and remove weight norm to model while loading sd apply_weight_norm(model.rnn) model.load_state_dict(sd) remove_weight_norm(model)
def detect(source, save_img=True): weights = opt.weights view_img = opt.view_img save_txt = opt.save_txt # Initialize set_logging() device = select_device(opt.device) half = device.type != 'cpu' # half precision only supported on CUDA # Load model model = attempt_load(weights, map_location=device) # load FP32 model #imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size if half: model.half() # to FP16 # Second-stage classifier classify = False #if classify: # modelc = load_classifier(name='resnet101', n=2) # initialize # modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval() img0 = source # BGR img = letterbox(img0, new_shape=output_size)[0] img = img[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416 img = np.ascontiguousarray(img) # 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 #img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img img = torch.from_numpy(img).to(device) im0s = img0 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 pred = model(img, augment=opt.augment)[0] # Apply NMS pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) # Apply Classifier if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process detections for i, det in enumerate(pred): # detections per image s, im0 = '', im0s s += '%gx%g ' % img.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh if det is not None and 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 += '%g %ss, ' % (n, names[int(c)]) # add to string # Write results for *xyxy, conf, cls in reversed(det): if save_img or view_img: # Add bbox to image logging.info(cls) if cls == 2 or cls == 5 or cls == 7: label = '%s %.2f' % (names[int(cls)], conf) plot_bbox_and_depth(xyxy, im0, label=label, color=colors[int(cls)]) #color_detection(im0, xyxy, color=colors[int(cls)]) logging.info('plot bbox')
def detect(save_img=False): img_size = 512 out = 'output' source = 'semioutput' weights = 'weights/yolov3-spp-ultralytics.pt' cfg_ = 'cfg/yolov3-spp.cfg' names_ = 'data/coco.names' fourcc = 'mp4' half = opt.half view_img = opt.view_img save_txt = opt.save_txt imgsz = img_size webcam = source == '0' or source.startswith('rtsp') or source.startswith( 'http') or source.endswith('.txt') # Initialize device = torch_utils.select_device( device='cpu' if ONNX_EXPORT else opt.device) if os.path.exists(out): shutil.rmtree(out) # delete output folder os.makedirs(out) # make new output folder # Initialize model model = Darknet(cfg_, imgsz) # Load weights attempt_download(weights) if weights.endswith('.pt'): # pytorch format model.load_state_dict( torch.load(weights, map_location=device)['model']) else: # darknet format load_darknet_weights(model, weights) # Second-stage classifier classify = False if classify: modelc = torch_utils.load_classifier(name='resnet101', n=2) # initialize modelc.load_state_dict( torch.load('weights/resnet101.pt', map_location=device)['model']) # load weights modelc.to(device).eval() # Eval mode model.to(device).eval() # Fuse Conv2d + BatchNorm2d layers # model.fuse() half = half and device.type != 'cpu' # half precision only supported on CUDA if half: model.half() # Set Dataloader vid_path, vid_writer = None, None if webcam: view_img = True torch.backends.cudnn.benchmark = True # set True to speed up constant image size inference dataset = LoadStreams(source, img_size=imgsz) else: save_img = True dataset = LoadImages(source, img_size=imgsz) # Get names and colors names = load_classes(names_) colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))] # Run inference t0 = time.time() img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img _ = model(img.half() if half else img.float() ) if device.type != 'cpu' else None # run once 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 = torch_utils.time_synchronized() pred = model(img, augment=opt.augment)[0] t2 = torch_utils.time_synchronized() # to float if half: pred = pred.float() # Apply NMS pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, multi_label=False, classes=opt.classes, agnostic=opt.agnostic_nms) # Apply Classifier if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process detections for i, det in enumerate(pred): # detections for image i if webcam: # batch_size >= 1 p, s, im0 = path[i], '%g: ' % i, im0s[i].copy() else: p, s, im0 = path, '', im0s save_path = str(Path(out) / Path(p).name) s += '%gx%g ' % img.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh if det is not None and len(det): # Rescale boxes from imgsz to im0 size det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() # Print results for c in det[:, -1].detach().unique(): n = (det[:, -1] == c).sum() # detections per class s += '%g %ss, ' % (n, names[int(c)]) # 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 with open(save_path[:save_path.rfind('.')] + '.txt', 'a') as file: file.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format if save_img or view_img: # Add bbox to image label = '%s %.2f' % (names[int(cls)], conf) plot_bbox_and_depth(xyxy, im0, label=label, color=colors[int(cls)]) color_detection(im0, xyxy, color=colors[int(cls)]) # Print time (inference + NMS) print('%sDone. (%.3fs)' % (s, t2 - t1)) # Stream results if view_img: cv2.imshow(p, im0) if cv2.waitKey(1) == ord('q'): # q to quit raise StopIteration # Save results (image with detections) if save_img: if dataset.mode == 'images': cv2.imwrite(save_path, im0) else: if vid_path != save_path: # new video vid_path = save_path if isinstance(vid_writer, cv2.VideoWriter): vid_writer.release( ) # release previous video writer 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)) vid_writer = cv2.VideoWriter( save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) vid_writer.write(im0) if save_txt or save_img: print('Results saved to %s' % os.getcwd() + os.sep + out) if platform == 'darwin': # MacOS os.system('open ' + save_path) print('Done. (%.3fs)' % (time.time() - t0))