def run( weights='yolov5s.pt', # model.pt path(s) source='data/images', # file/dir/URL/glob, 0 for webcam imgsz=640, # inference size (pixels) conf_thres=0.25, # confidence threshold iou_thres=0.45, # NMS IOU threshold max_det=1000, # maximum detections per image device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu view_img=False, # show results save_txt=False, # save results to *.txt save_conf=False, # save confidences in --save-txt labels save_crop=False, # save cropped prediction boxes nosave=False, # do not save images/videos classes=None, # filter by class: --class 0, or --class 0 2 3 agnostic_nms=False, # class-agnostic NMS augment=False, # augmented inference visualize=False, # visualize features update=False, # update all models project='runs/detect', # save results to project/name name='exp', # save results to project/name exist_ok=False, # existing project/name ok, do not increment line_thickness=3, # bounding box thickness (pixels) hide_labels=False, # hide labels hide_conf=False, # hide confidences half=False, # use FP16 half-precision inference ): save_img = not 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 = 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 # Initialize set_logging() device = select_device(device) half &= device.type != 'cpu' # half precision only supported on CUDA # Load model w = weights[0] if isinstance(weights, list) else weights classify, suffix = False, Path(w).suffix.lower() pt, onnx, tflite, pb, saved_model = ( suffix == x for x in ['.pt', '.onnx', '.tflite', '.pb', '']) # backend stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults if pt: model = attempt_load(weights, map_location=device) # load FP32 model stride = int(model.stride.max()) # model stride names = model.module.names if hasattr( model, 'module') else model.names # get class names if half: model.half() # to FP16 if classify: # second-stage classifier modelc = load_classifier(name='resnet50', n=2) # initialize modelc.load_state_dict( torch.load('resnet50.pt', map_location=device)['model']).to(device).eval() elif onnx: check_requirements(('onnx', 'onnxruntime')) import onnxruntime session = onnxruntime.InferenceSession(w, None) else: # TensorFlow models check_requirements(('tensorflow>=2.4.1', )) import tensorflow as tf if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt def wrap_frozen_graph(gd, inputs, outputs): x = tf.compat.v1.wrap_function( lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped import return x.prune( tf.nest.map_structure(x.graph.as_graph_element, inputs), tf.nest.map_structure(x.graph.as_graph_element, outputs)) graph_def = tf.Graph().as_graph_def() graph_def.ParseFromString(open(w, 'rb').read()) frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0") elif saved_model: model = tf.keras.models.load_model(w) elif tflite: interpreter = tf.lite.Interpreter( model_path=w) # load TFLite model interpreter.allocate_tensors() # allocate input_details = interpreter.get_input_details() # inputs output_details = interpreter.get_output_details() # outputs int8 = input_details[0][ 'dtype'] == np.uint8 # is TFLite quantized uint8 model imgsz = check_img_size(imgsz, s=stride) # check image size ascii = is_ascii(names) # names are ascii (use PIL for UTF-8) # 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 # Run inference if pt and device.type != 'cpu': model( torch.zeros(1, 3, *imgsz).to(device).type_as( next(model.parameters()))) # run once t0 = time.time() for path, img, im0s, vid_cap in dataset: if onnx: img = img.astype('float32') else: img = torch.from_numpy(img).to(device) img = img.half() if half else img.float() # uint8 to fp16/32 img = img / 255.0 # 0 - 255 to 0.0 - 1.0 if len(img.shape) == 3: img = img[None] # expand for batch dim # Inference t1 = time_sync() if pt: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred = model(img, augment=augment, visualize=visualize)[0] elif onnx: pred = torch.tensor( session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img})) else: # tensorflow model (tflite, pb, saved_model) imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy if pb: pred = frozen_func(x=tf.constant(imn)).numpy() elif saved_model: pred = model(imn, training=False).numpy() elif tflite: if int8: scale, zero_point = input_details[0]['quantization'] imn = (imn / scale + zero_point).astype( np.uint8) # de-scale interpreter.set_tensor(input_details[0]['index'], imn) interpreter.invoke() pred = interpreter.get_tensor(output_details[0]['index']) if int8: scale, zero_point = output_details[0]['quantization'] pred = (pred.astype(np.float32) - zero_point) * scale # re-scale pred[..., 0] *= imgsz[1] # x pred[..., 1] *= imgsz[0] # y pred[..., 2] *= imgsz[1] # w pred[..., 3] *= imgsz[0] # h pred = torch.tensor(pred) # NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) t2 = time_sync() # Second-stage classifier (optional) if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process predictions for i, det in enumerate(pred): # detections per image if webcam: # batch_size >= 1 p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy( ), dataset.count else: p, s, im0, frame = path, '', im0s.copy(), 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 imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, pil=not ascii) 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 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 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) # Print time (inference + NMS) print(f'{s}Done. ({t2 - t1:.3f}s)') # Stream results im0 = annotator.result() if view_img: 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 += '.mp4' vid_writer[i] = cv2.VideoWriter( save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) 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 '' print(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights) # update model (to fix SourceChangeWarning) print(f'Done. ({time.time() - t0:.3f}s)')
def run( data, weights=None, # model.pt path(s) batch_size=32, # batch size imgsz=640, # inference size (pixels) conf_thres=0.001, # confidence threshold iou_thres=0.6, # NMS IoU threshold task='val', # train, val, test, speed or study device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu single_cls=False, # treat as single-class dataset augment=False, # augmented inference verbose=False, # verbose output save_txt=False, # save results to *.txt save_hybrid=False, # save label+prediction hybrid results to *.txt save_conf=False, # save confidences in --save-txt labels save_json=False, # save a COCO-JSON results file project=ROOT / 'runs/val', # save to project/name name='exp', # save to project/name exist_ok=False, # existing project/name ok, do not increment half=True, # use FP16 half-precision inference dnn=False, # use OpenCV DNN for ONNX inference model=None, dataloader=None, save_dir=Path(''), plots=True, callbacks=Callbacks(), compute_loss=None, ): # Initialize/load model and set device training = model is not None if training: # called by train.py device, pt = next( model.parameters()).device, True # get model device, PyTorch model half &= device.type != 'cpu' # half precision only supported on CUDA model.half() if half else model.float() else: # called directly device = select_device(device, batch_size=batch_size) # 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 model = DetectMultiBackend(weights, device=device, dnn=dnn) stride, pt = model.stride, model.pt imgsz = check_img_size(imgsz, s=stride) # check image size half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA if pt: model.model.half() if half else model.model.float() else: half = False batch_size = 1 # export.py models default to batch-size 1 device = torch.device('cpu') LOGGER.info( f'Forcing --batch-size 1 square inference shape(1,3,{imgsz},{imgsz}) for non-PyTorch backends' ) # Data data = check_dataset(data) # check # Configure model.eval() is_coco = isinstance(data.get('val'), str) and data['val'].endswith( 'coco/val2017.txt') # COCO dataset nc = 1 if single_cls else int(data['nc']) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95 niou = iouv.numel() # Dataloader if not training: if pt and device.type != 'cpu': model( torch.zeros(1, 3, imgsz, imgsz).to(device).type_as( next(model.model.parameters()))) # warmup pad = 0.0 if task == 'speed' else 0.5 task = task if task in ( 'train', 'val', 'test') else 'val' # path to train/val/test images dataloader = create_dataloader(data[task], imgsz, batch_size, stride, single_cls, pad=pad, rect=pt, prefix=colorstr(f'{task}: '))[0] seen = 0 confusion_matrix = ConfusionMatrix(nc=nc) names = { k: v for k, v in enumerate( model.names if hasattr(model, 'names') else model.module.names) } class_map = coco80_to_coco91_class() if is_coco else list(range(1000)) s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', '[email protected]', '[email protected]:.95') dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class = [], [], [], [] pbar = tqdm(dataloader, desc=s, ncols=NCOLS, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}') # progress bar for batch_i, (im, targets, paths, shapes) in enumerate(pbar): t1 = time_sync() if pt: im = im.to(device, non_blocking=True) targets = targets.to(device) im = im.half() if half else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 nb, _, height, width = im.shape # batch size, channels, height, width t2 = time_sync() dt[0] += t2 - t1 # Inference out, train_out = model(im) if training else model( im, augment=augment, val=True) # inference, loss outputs dt[1] += time_sync() - t2 # Loss if compute_loss: loss += compute_loss([x.float() for x in train_out], targets)[1] # box, obj, cls # NMS targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling t3 = time_sync() out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) dt[2] += time_sync() - t3 # Metrics for si, pred in enumerate(out): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class path, shape = Path(paths[si]), shapes[si][0] seen += 1 if len(pred) == 0: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Predictions if single_cls: pred[:, 5] = 0 predn = pred.clone() scale_coords(im[si].shape[1:], predn[:, :4], shape, shapes[si][1]) # native-space pred # Evaluate if nl: tbox = xywh2xyxy(labels[:, 1:5]) # target boxes scale_coords(im[si].shape[1:], tbox, shape, shapes[si][1]) # native-space labels labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels correct = process_batch(predn, labelsn, iouv) if plots: confusion_matrix.process_batch(predn, labelsn) else: correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool) stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # (correct, conf, pcls, tcls) # Save/log if save_txt: save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt')) if save_json: save_one_json(predn, jdict, path, class_map) # append to COCO-JSON dictionary callbacks.run('on_val_image_end', pred, predn, path, names, im[si]) # Plot images if plots and batch_i < 3: f = save_dir / f'val_batch{batch_i}_labels.jpg' # labels Thread(target=plot_images, args=(im, targets, paths, f, names), daemon=True).start() f = save_dir / f'val_batch{batch_i}_pred.jpg' # predictions Thread(target=plot_images, args=(im, output_to_target(out), paths, f, names), daemon=True).start() # Compute metrics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats) and stats[0].any(): p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names) ap50, ap = ap[:, 0], ap.mean(1) # [email protected], [email protected]:0.95 mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1) # Print results pf = '%20s' + '%11i' * 2 + '%11.3g' * 4 # print format LOGGER.info(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) # Print results per class if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats): for i, c in enumerate(ap_class): LOGGER.info(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1E3 for x in dt) # speeds per image if not training: shape = (batch_size, 3, imgsz, imgsz) LOGGER.info( f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t) # Plots if plots: confusion_matrix.plot(save_dir=save_dir, names=list(names.values())) callbacks.run('on_val_end') # Save JSON if save_json and len(jdict): w = Path(weights[0] if isinstance(weights, list) else weights ).stem if weights is not None else '' # weights anno_json = str( Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json') # annotations json pred_json = str(save_dir / f"{w}_predictions.json") # predictions json LOGGER.info(f'\nEvaluating pycocotools mAP... saving {pred_json}...') with open(pred_json, 'w') as f: json.dump(jdict, f) try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb check_requirements(['pycocotools']) from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval anno = COCO(anno_json) # init annotations api pred = anno.loadRes(pred_json) # init predictions api eval = COCOeval(anno, pred, 'bbox') if is_coco: eval.params.imgIds = [ int(Path(x).stem) for x in dataloader.dataset.img_files ] # image IDs to evaluate eval.evaluate() eval.accumulate() eval.summarize() map, map50 = eval.stats[: 2] # update results ([email protected]:0.95, [email protected]) except Exception as e: LOGGER.info(f'pycocotools unable to run: {e}') # Return results model.float() # for training if not training: 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}") maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def run( weights=ROOT / 'yolov5s.pt', # model.pt path(s) source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam data=ROOT / 'data/coco128.yaml', # dataset.yaml path imgsz=(640, 640), # inference size (height, width) conf_thres=0.25, # confidence threshold iou_thres=0.45, # NMS IOU threshold max_det=1000, # maximum detections per image device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu view_img=False, # show results save_txt=False, # save results to *.txt save_conf=False, # save confidences in --save-txt labels save_crop=False, # save cropped prediction boxes nosave=False, # do not save images/videos classes=None, # filter by class: --class 0, or --class 0 2 3 agnostic_nms=False, # class-agnostic NMS augment=False, # augmented inference visualize=False, # visualize features update=False, # update all models project=ROOT / 'runs/detect', # save results to project/name name='exp', # save results to project/name exist_ok=False, # existing project/name ok, do not increment line_thickness=3, # bounding box thickness (pixels) hide_labels=False, # hide labels hide_conf=False, # hide confidences half=False, # use FP16 half-precision inference dnn=False, # use OpenCV DNN for ONNX inference ): 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 # Run inference model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup seen, windows, dt = 0, [], [0.0, 0.0, 0.0] for path, im, im0s, vid_cap, s in dataset: 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): 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: if p not in windows: windows.append(p) cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0]) 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 forward(self, imgs, size=640, augment=False, profile=False): # Inference from various sources. For height=640, width=1280, RGB images example inputs are: # file: imgs = 'data/images/zidane.jpg' # str or PosixPath # URI: = 'https://ultralytics.com/images/zidane.jpg' # OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3) # PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3) # numpy: = np.zeros((640,1280,3)) # HWC # torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values) # multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images t = [time_sync()] p = next(self.model.parameters()) if self.pt else torch.zeros( 1, device=self.model.device) # for device, type autocast = self.amp and (p.device.type != 'cpu' ) # Automatic Mixed Precision (AMP) inference if isinstance(imgs, torch.Tensor): # torch with amp.autocast(autocast): return self.model( imgs.to(p.device).type_as(p), augment, profile) # inference # Pre-process n, imgs = (len(imgs), list(imgs)) if isinstance( imgs, (list, tuple)) else (1, [imgs]) # number, list of images shape0, shape1, files = [], [], [ ] # image and inference shapes, filenames for i, im in enumerate(imgs): f = f'image{i}' # filename if isinstance(im, (str, Path)): # filename or uri im, f = Image.open( requests.get(im, stream=True).raw if str(im). startswith('http') else im), im im = np.asarray(exif_transpose(im)) elif isinstance(im, Image.Image): # PIL Image im, f = np.asarray( exif_transpose(im)), getattr(im, 'filename', f) or f files.append(Path(f).with_suffix('.jpg').name) if im.shape[0] < 5: # image in CHW im = im.transpose( (1, 2, 0)) # reverse dataloader .transpose(2, 0, 1) im = im[..., :3] if im.ndim == 3 else np.tile( im[..., None], 3) # enforce 3ch input s = im.shape[:2] # HWC shape0.append(s) # image shape g = (size / max(s)) # gain shape1.append([y * g for y in s]) imgs[i] = im if im.data.contiguous else np.ascontiguousarray( im) # update shape1 = [ make_divisible(x, self.stride) if self.pt else size for x in np.array(shape1).max(0) ] # inf shape x = [letterbox(im, shape1, auto=False)[0] for im in imgs] # pad x = np.ascontiguousarray(np.array(x).transpose( (0, 3, 1, 2))) # stack and BHWC to BCHW x = torch.from_numpy(x).to( p.device).type_as(p) / 255 # uint8 to fp16/32 t.append(time_sync()) with amp.autocast(autocast): # Inference y = self.model(x, augment, profile) # forward t.append(time_sync()) # Post-process y = non_max_suppression(y if self.dmb else y[0], self.conf, self.iou, self.classes, self.agnostic, self.multi_label, max_det=self.max_det) # NMS for i in range(n): scale_coords(shape1, y[i][:, :4], shape0[i]) t.append(time_sync()) return Detections(imgs, y, files, t, self.names, x.shape)
def detect( self, weights='checkpoints/best_s.pt', # model.pt path(s) source='test', # file/dir/URL/glob, 0 for webcam imgsz=640, # inference size (pixels) conf_thres=0.25, # confidence threshold iou_thres=0.45, # NMS IOU threshold max_det=1000, # maximum detections per image device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu view_img=False, # show results save_txt=False, # save results to *.txt save_conf=False, # save confidences in --save-txt labels save_crop=False, # save cropped prediction boxes nosave=False, # do not save images/videos classes=None, # filter by class: --class 0, or --class 0 2 3 agnostic_nms=False, # class-agnostic NMS augment=False, # augmented inference visualize=False, # visualize features update=False, # update all models project='result', # save results to project path exist_ok=False, # existing project/name ok, do not increment line_thickness=3, # bounding box thickness (pixels) hide_labels=False, # hide labels hide_conf=False, # hide confidences half=False, # use FP16 half-precision inference ): save_img = not nosave and not source.endswith( '.txt') # save inference images # Directories save_dir = Path(project) (save_dir / 'labels' if save_txt else save_dir).mkdir( parents=True, exist_ok=True) # make dir # Initialize set_logging() device = select_device(device) half &= device.type != 'cpu' # half precision only supported on CUDA # Load model w = weights[0] if isinstance(weights, list) else weights classify, pt, onnx = False, w.endswith('.pt'), w.endswith( '.onnx') # inference type stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults if pt: model = attempt_load(weights, map_location=device) # load FP32 model stride = int(model.stride.max()) # model stride names = model.module.names if hasattr( model, 'module') else model.names # get class names if half: model.half() # to FP16 if classify: # second-stage classifier modelc = load_classifier(name='resnet50', n=2) # initialize modelc.load_state_dict( torch.load( 'resnet50.pt', map_location=device)['model']).to(device).eval() elif onnx: check_requirements(('onnx', 'onnxruntime')) import onnxruntime session = onnxruntime.InferenceSession(w, None) imgsz = check_img_size(imgsz, s=stride) # check image size # Dataloader dataset = LoadImages(source, img_size=imgsz, stride=stride) bs = 1 # batch_size vid_path, vid_writer = [None] * bs, [None] * bs # Run inference if pt and 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: if pt: img = torch.from_numpy(img).to(device) img = img.half() if half else img.float() # uint8 to fp16/32 elif onnx: img = img.astype('float32') img /= 255.0 # 0 - 255 to 0.0 - 1.0 if len(img.shape) == 3: img = img[None] # expand for batch dim # Inference t1 = time_sync() if pt: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred = model(img, augment=augment, visualize=visualize)[0] elif onnx: pred = torch.tensor( session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img})) # NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) t2 = time_sync() # Second-stage classifier (optional) if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process predictions bbox_pred = [] for i, det in enumerate(pred): # detections per image bbox_pred.append(det.cpu().numpy()[:, :-1]) p, s, im0, frame = path, '', im0s.copy(), 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 imc = im0.copy() if save_crop else im0 # for save_crop 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 if save_txt: f = open(txt_path + '.txt', 'w') 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 = ( *xyxy, conf ) # if save_conf else (cls, *xywh) # label format 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}') plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=line_thickness) if save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) if save_txt: f.close() # Print time (inference + NMS) print(f'{s}Done. ({t2 - t1:.3f}s)') # Stream results if view_img: 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 += '.mp4' vid_writer[i] = cv2.VideoWriter( save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) 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 '' print(f"Results saved to {save_dir}{s}") if update: strip_optimizer( weights) # update model (to fix SourceChangeWarning) print(f'Done. ({time.time() - t0:.3f}s)') return bbox_pred