def __call__(self, p, targets): # predictions, targets, model device = targets.device lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros( 1, device=device), torch.zeros(1, device=device) tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets # Losses for i, pi in enumerate(p): # layer index, layer predictions b, a, gj, gi = indices[i] # image, anchor, gridy, gridx tobj = torch.zeros_like(pi[..., 0], device=device) # target obj n = b.shape[0] # number of targets if n: ps = pi[b, a, gj, gi] # prediction subset corresponding to targets # Regression pxy = ps[:, :2].sigmoid() * 2. - 0.5 pwh = (ps[:, 2:4].sigmoid() * 2)**2 * anchors[i] pbox = torch.cat((pxy, pwh), 1) # predicted box iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target) lbox += (1.0 - iou).mean() # iou loss # Objectness score_iou = iou.detach().clamp(0).type(tobj.dtype) if self.sort_obj_iou: sort_id = torch.argsort(score_iou) b, a, gj, gi, score_iou = b[sort_id], a[sort_id], gj[ sort_id], gi[sort_id], score_iou[sort_id] tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * score_iou # iou ratio # Classification if self.nc > 1: # cls loss (only if multiple classes) t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets t[range(n), tcls[i]] = self.cp lcls += self.BCEcls(ps[:, 5:], t) # BCE # Append targets to text file # with open('targets.txt', 'a') as file: # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] obji = self.BCEobj(pi[..., 4], tobj) lobj += obji * self.balance[i] # obj loss if self.autobalance: self.balance[i] = self.balance[ i] * 0.9999 + 0.0001 / obji.detach().item() if self.autobalance: self.balance = [x / self.balance[self.ssi] for x in self.balance] lbox *= self.hyp['box'] lobj *= self.hyp['obj'] lcls *= self.hyp['cls'] bs = tobj.shape[0] # batch size return (lbox + lobj + lcls) * bs, torch.cat( (lbox, lobj, lcls)).detach()
def __call__(self, p, targets): # predictions, targets lcls = torch.zeros(1, device=self.device) # class loss lbox = torch.zeros(1, device=self.device) # box loss lobj = torch.zeros(1, device=self.device) # object loss tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets # Losses for i, pi in enumerate(p): # layer index, layer predictions b, a, gj, gi = indices[i] # image, anchor, gridy, gridx tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj n = b.shape[0] # number of targets if n: # pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1) # faster, requires torch 1.8.0 pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1) # target-subset of predictions # Regression pxy = pxy.sigmoid() * 2 - 0.5 pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i] pbox = torch.cat((pxy, pwh), 1) # predicted box iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target) lbox += (1.0 - iou).mean() # iou loss # Objectness iou = iou.detach().clamp(0).type(tobj.dtype) if self.sort_obj_iou: j = iou.argsort() b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j] if self.gr < 1: iou = (1.0 - self.gr) + self.gr * iou tobj[b, a, gj, gi] = iou # iou ratio # Classification if self.nc > 1: # cls loss (only if multiple classes) t = torch.full_like(pcls, self.cn, device=self.device) # targets t[range(n), tcls[i]] = self.cp lcls += self.BCEcls(pcls, t) # BCE # Append targets to text file # with open('targets.txt', 'a') as file: # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] obji = self.BCEobj(pi[..., 4], tobj) lobj += obji * self.balance[i] # obj loss if self.autobalance: self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item() if self.autobalance: self.balance = [x / self.balance[self.ssi] for x in self.balance] lbox *= self.hyp['box'] lobj *= self.hyp['obj'] lcls *= self.hyp['cls'] bs = tobj.shape[0] # batch size return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()
def detect( model="mobilenet_thin", # A model option for being cool 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 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 ): w, h = 432, 368 e = TfPoseEstimator(get_graph_path(model), target_size=(w, h)) 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 = Path(project) #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 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 image size names = model.module.names if hasattr( model, 'module') else model.names # get class names 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() # 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) # Run inference breakCond = False 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) # Openpose getting keypoints and individual crops print("\n") myImg = im0s.copy() keypoints, humans = getKeyPoints(myImg, e, w, h) crops = [ getCrop(point[0], myImg, 10, device, point[1] / 2) for point in keypoints ] # Inference t1 = time_synchronized() pred = model(img, augment=augment)[0] # Apply NMS pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) t2 = time_synchronized() # Need to adjust bboxes to full image if len(pred) > 0: breakCond = True # Apply Classifier if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process detections 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, 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 # Check if any overlap between keypoint and det (handheld weapon) for detection in det: for crop in crops: if bbox_iou(detection, crop) > 0: cv2.putText(im0, "Spider-Sense Tingling!", (30, 90), cv2.FONT_HERSHEY_SIMPLEX, 3, (255, 0, 0), 5) break # 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}') 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) # write keypoint boxes for *xyxy, conf, cls in reversed(crops): plot_one_box(xyxy, imc, label="keyP", color=colors(c, True), line_thickness=line_thickness) # Stream results if view_img: cv2.imshow(str(p), im0) cv2.waitKey(1) # 1 millisecond # Save results (image with detections) im0 = TfPoseEstimator.draw_humans(im0, humans, imgcopy=False) if save_img: if dataset.mode == 'image': cv2.imwrite(save_path, im0) 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)) 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) 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)')