def detect_onet(self, im, dets): """Get face candidates using onet Parameters: ---------- im: numpy array input image array dets: numpy array detection results of rnet Returns: ------- boxes_align: numpy array boxes after calibration landmarks_align: numpy array landmarks after calibration """ h, w, c = im.shape if dets is None: return None, None dets = self.square_bbox(dets) dets[:, 0:4] = np.round(dets[:, 0:4]) [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h) num_boxes = dets.shape[0] # cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32) cropped_ims_tensors = [] for i in range(num_boxes): tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8) tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1, x[i]:ex[i] + 1, :] crop_im = cv2.resize(tmp, (48, 48)) crop_im_tensor = image_tools.convert_image_to_tensor(crop_im) # cropped_ims_tensors[i, :, :, :] = crop_im_tensor cropped_ims_tensors.append(crop_im_tensor) feed_imgs = Variable(torch.stack(cropped_ims_tensors)) if self.rnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg, landmark = self.onet_detector(feed_imgs) cls_map = cls_map.cpu().data.numpy() reg = reg.cpu().data.numpy() landmark = landmark.cpu().data.numpy() keep_inds = np.where(cls_map > self.thresh[2])[0] if len(keep_inds) > 0: boxes = dets[keep_inds] cls = cls_map[keep_inds] reg = reg[keep_inds] landmark = landmark[keep_inds] else: return None, None keep = utils.nms(boxes, 0.7, mode="Minimum") if len(keep) == 0: return None, None keep_cls = cls[keep] keep_boxes = boxes[keep] keep_reg = reg[keep] keep_landmark = landmark[keep] bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1 bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1 align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh align_landmark_topx = keep_boxes[:, 0] align_landmark_topy = keep_boxes[:, 1] boxes_align = np.vstack([ align_topx, align_topy, align_bottomx, align_bottomy, keep_cls[:, 0], # align_topx + keep_landmark[:, 0] * bw, # align_topy + keep_landmark[:, 1] * bh, # align_topx + keep_landmark[:, 2] * bw, # align_topy + keep_landmark[:, 3] * bh, # align_topx + keep_landmark[:, 4] * bw, # align_topy + keep_landmark[:, 5] * bh, # align_topx + keep_landmark[:, 6] * bw, # align_topy + keep_landmark[:, 7] * bh, # align_topx + keep_landmark[:, 8] * bw, # align_topy + keep_landmark[:, 9] * bh, ]) boxes_align = boxes_align.T landmark = np.vstack([ align_landmark_topx + keep_landmark[:, 0] * bw, align_landmark_topy + keep_landmark[:, 1] * bh, align_landmark_topx + keep_landmark[:, 2] * bw, align_landmark_topy + keep_landmark[:, 3] * bh, align_landmark_topx + keep_landmark[:, 4] * bw, align_landmark_topy + keep_landmark[:, 5] * bh, align_landmark_topx + keep_landmark[:, 6] * bw, align_landmark_topy + keep_landmark[:, 7] * bh, align_landmark_topx + keep_landmark[:, 8] * bw, align_landmark_topy + keep_landmark[:, 9] * bh, ]) landmark_align = landmark.T return boxes_align, landmark_align
def detect_rnet(self, im, dets): """Get face candidates using rnet Parameters: ---------- im: numpy array input image array dets: numpy array detection results of pnet Returns: ------- boxes: numpy array detected boxes before calibration boxes_align: numpy array boxes after calibration """ h, w, c = im.shape if dets is None: return None, None dets = self.square_bbox(dets) dets[:, 0:4] = np.round(dets[:, 0:4]) [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h) num_boxes = dets.shape[0] ''' # helper for setting RNet batch size batch_size = self.rnet_detector.batch_size ratio = float(num_boxes) / batch_size if ratio > 3 or ratio < 0.3: print "You may need to reset RNet batch size if this info appears frequently, \ face candidates:%d, current batch_size:%d"%(num_boxes, batch_size) ''' # cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32) cropped_ims_tensors = [] for i in range(num_boxes): tmp = np.zeros((tmph[i], tmpw[i], 3), dtype=np.uint8) tmp[dy[i]:edy[i] + 1, dx[i]:edx[i] + 1, :] = im[y[i]:ey[i] + 1, x[i]:ex[i] + 1, :] crop_im = cv2.resize(tmp, (24, 24)) crop_im_tensor = image_tools.convert_image_to_tensor(crop_im) # cropped_ims_tensors[i, :, :, :] = crop_im_tensor cropped_ims_tensors.append(crop_im_tensor) feed_imgs = Variable(torch.stack(cropped_ims_tensors)) if self.rnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg = self.rnet_detector(feed_imgs) cls_map = cls_map.cpu().data.numpy() reg = reg.cpu().data.numpy() # landmark = landmark.cpu().data.numpy() keep_inds = np.where(cls_map > self.thresh[1])[0] if len(keep_inds) > 0: boxes = dets[keep_inds] cls = cls_map[keep_inds] reg = reg[keep_inds] # landmark = landmark[keep_inds] else: return None, None keep = utils.nms(boxes, 0.7) if len(keep) == 0: return None, None keep_cls = cls[keep] keep_boxes = boxes[keep] keep_reg = reg[keep] # keep_landmark = landmark[keep] bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1 bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1 boxes = np.vstack([ keep_boxes[:, 0], keep_boxes[:, 1], keep_boxes[:, 2], keep_boxes[:, 3], keep_cls[:, 0], # keep_boxes[:,0] + keep_landmark[:, 0] * bw, # keep_boxes[:,1] + keep_landmark[:, 1] * bh, # keep_boxes[:,0] + keep_landmark[:, 2] * bw, # keep_boxes[:,1] + keep_landmark[:, 3] * bh, # keep_boxes[:,0] + keep_landmark[:, 4] * bw, # keep_boxes[:,1] + keep_landmark[:, 5] * bh, # keep_boxes[:,0] + keep_landmark[:, 6] * bw, # keep_boxes[:,1] + keep_landmark[:, 7] * bh, # keep_boxes[:,0] + keep_landmark[:, 8] * bw, # keep_boxes[:,1] + keep_landmark[:, 9] * bh, ]) align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh boxes_align = np.vstack([ align_topx, align_topy, align_bottomx, align_bottomy, keep_cls[:, 0], # align_topx + keep_landmark[:, 0] * bw, # align_topy + keep_landmark[:, 1] * bh, # align_topx + keep_landmark[:, 2] * bw, # align_topy + keep_landmark[:, 3] * bh, # align_topx + keep_landmark[:, 4] * bw, # align_topy + keep_landmark[:, 5] * bh, # align_topx + keep_landmark[:, 6] * bw, # align_topy + keep_landmark[:, 7] * bh, # align_topx + keep_landmark[:, 8] * bw, # align_topy + keep_landmark[:, 9] * bh, ]) boxes = boxes.T boxes_align = boxes_align.T return boxes, boxes_align
def detect_pnet(self, im): """Get face candidates through pnet Parameters: ---------- im: numpy array input image array Returns: ------- boxes: numpy array detected boxes before calibration boxes_align: numpy array boxes after calibration """ # im = self.unique_image_format(im) h, w, c = im.shape net_size = 12 current_scale = float( net_size) / self.min_face_size # find initial scale im_resized = self.resize_image(im, current_scale) current_height, current_width, _ = im_resized.shape # fcn all_boxes = list() while min(current_height, current_width) > net_size: feed_imgs = [] image_tensor = image_tools.convert_image_to_tensor(im_resized) feed_imgs.append(image_tensor) feed_imgs = torch.stack(feed_imgs) feed_imgs = Variable(feed_imgs) if self.pnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg = self.pnet_detector(feed_imgs) cls_map_np = image_tools.convert_chwTensor_to_hwcNumpy( cls_map.cpu()) reg_np = image_tools.convert_chwTensor_to_hwcNumpy(reg.cpu()) # landmark_np = image_tools.convert_chwTensor_to_hwcNumpy(landmark.cpu()) boxes = self.generate_bounding_box(cls_map_np[0, :, :], reg_np, current_scale, self.thresh[0]) current_scale *= self.scale_factor im_resized = self.resize_image(im, current_scale) current_height, current_width, _ = im_resized.shape if boxes.size == 0: continue keep = utils.nms(boxes[:, :5], 0.5, 'Union') boxes = boxes[keep] all_boxes.append(boxes) if len(all_boxes) == 0: return None, None all_boxes = np.vstack(all_boxes) # merge the detection from first stage keep = utils.nms(all_boxes[:, 0:5], 0.7, 'Union') all_boxes = all_boxes[keep] # boxes = all_boxes[:, :5] bw = all_boxes[:, 2] - all_boxes[:, 0] + 1 bh = all_boxes[:, 3] - all_boxes[:, 1] + 1 # landmark_keep = all_boxes[:, 9:].reshape((5,2)) boxes = np.vstack([ all_boxes[:, 0], all_boxes[:, 1], all_boxes[:, 2], all_boxes[:, 3], all_boxes[:, 4], # all_boxes[:, 0] + all_boxes[:, 9] * bw, # all_boxes[:, 1] + all_boxes[:,10] * bh, # all_boxes[:, 0] + all_boxes[:, 11] * bw, # all_boxes[:, 1] + all_boxes[:, 12] * bh, # all_boxes[:, 0] + all_boxes[:, 13] * bw, # all_boxes[:, 1] + all_boxes[:, 14] * bh, # all_boxes[:, 0] + all_boxes[:, 15] * bw, # all_boxes[:, 1] + all_boxes[:, 16] * bh, # all_boxes[:, 0] + all_boxes[:, 17] * bw, # all_boxes[:, 1] + all_boxes[:, 18] * bh ]) boxes = boxes.T align_topx = all_boxes[:, 0] + all_boxes[:, 5] * bw align_topy = all_boxes[:, 1] + all_boxes[:, 6] * bh align_bottomx = all_boxes[:, 2] + all_boxes[:, 7] * bw align_bottomy = all_boxes[:, 3] + all_boxes[:, 8] * bh # refine the boxes boxes_align = np.vstack([ align_topx, align_topy, align_bottomx, align_bottomy, all_boxes[:, 4], # align_topx + all_boxes[:,9] * bw, # align_topy + all_boxes[:,10] * bh, # align_topx + all_boxes[:,11] * bw, # align_topy + all_boxes[:,12] * bh, # align_topx + all_boxes[:,13] * bw, # align_topy + all_boxes[:,14] * bh, # align_topx + all_boxes[:,15] * bw, # align_topy + all_boxes[:,16] * bh, # align_topx + all_boxes[:,17] * bw, # align_topy + all_boxes[:,18] * bh, ]) boxes_align = boxes_align.T return boxes, boxes_align
def detect_onet(self, im, dets): """Get face candidates using onet Parameters: ---------- im: numpy array input image array dets: numpy array detection results of rnet Returns: ------- boxes_align: numpy array boxes after calibration landmarks_align: numpy array landmarks after calibration """ _, _, h, w = im.shape if dets is None: return None, None dets = self.square_bbox(dets) dets[:, 0:4] = torch.round(dets[:, 0:4]) [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h) num_boxes = dets.shape[0] # cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32) cropped_ims_tensors = [] for i in range(num_boxes): tmp = self.tensortype.FloatTensor(1, 3, tmph[i], tmpw[i]).fill_(0) tmp[..., dy[i]:edy[i] + 1, dx[i]:edx[i] + 1] = im[..., y[i]:ey[i] + 1, x[i]:ex[i] + 1] crop_im = F.interpolate(tmp, size=(48, 48)) crop_im_tensor = crop_im # cropped_ims_tensors[i, :, :, :] = crop_im_tensor cropped_ims_tensors.append(crop_im_tensor) feed_imgs = torch.cat(cropped_ims_tensors) if self.rnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg, landmark = self.onet_detector(feed_imgs) keep_inds = (cls_map.squeeze() > self.thresh[2]).nonzero().squeeze() if keep_inds.dim() > 0 and len(keep_inds) > 0: boxes = dets[keep_inds] _cls = cls_map[keep_inds] reg = reg[keep_inds] landmark = landmark[keep_inds] else: return None, None keep = utils.nms(boxes, 0.7, mode="Minimum") if len(keep) == 0: return None, None keep_cls = _cls[keep] keep_boxes = boxes[keep] keep_reg = reg[keep] keep_landmark = landmark[keep] bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1 bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1 align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh align_landmark_topx = keep_boxes[:, 0] align_landmark_topy = keep_boxes[:, 1] boxes_align = torch.stack([ align_topx, align_topy, align_bottomx, align_bottomy, keep_cls[:, 0], ], dim=-1) landmark = torch.stack([ align_landmark_topx + keep_landmark[:, 0] * bw, align_landmark_topy + keep_landmark[:, 1] * bh, align_landmark_topx + keep_landmark[:, 2] * bw, align_landmark_topy + keep_landmark[:, 3] * bh, align_landmark_topx + keep_landmark[:, 4] * bw, align_landmark_topy + keep_landmark[:, 5] * bh, align_landmark_topx + keep_landmark[:, 6] * bw, align_landmark_topy + keep_landmark[:, 7] * bh, align_landmark_topx + keep_landmark[:, 8] * bw, align_landmark_topy + keep_landmark[:, 9] * bh, ], dim=-1) return boxes_align, landmark
def detect_rnet(self, im, dets): """Get face candidates using rnet Parameters: ---------- im: torch Tensor 1x3xHxW input image array dets: numpy array detection results of pnet Returns: ------- boxes: numpy array detected boxes before calibration boxes_align: numpy array boxes after calibration """ _, _, h, w = im.shape if dets is None: return None, None dets = self.square_bbox(dets) dets[:, 0:4] = torch.round(dets[:, 0:4]) [dy, edy, dx, edx, y, ey, x, ex, tmpw, tmph] = self.pad(dets, w, h) num_boxes = dets.shape[0] if num_boxes == 0: return None, None ''' # helper for setting RNet batch size batch_size = self.rnet_detector.batch_size ratio = float(num_boxes) / batch_size if ratio > 3 or ratio < 0.3: print "You may need to reset RNet batch size if this info appears frequently, \ face candidates:%d, current batch_size:%d"%(num_boxes, batch_size) ''' # cropped_ims_tensors = np.zeros((num_boxes, 3, 24, 24), dtype=np.float32) cropped_ims_tensors = [] for i in range(num_boxes): tmp = self.tensortype.FloatTensor(1, 3, tmph[i], tmpw[i]).fill_(0) tmp[..., dy[i]:edy[i] + 1, dx[i]:edx[i] + 1] = im[..., y[i]:ey[i] + 1, x[i]:ex[i] + 1] crop_im = F.interpolate(tmp, size=(24, 24)) crop_im_tensor = crop_im cropped_ims_tensors.append(crop_im_tensor) feed_imgs = torch.cat(cropped_ims_tensors) if self.rnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg = self.rnet_detector(feed_imgs) cls_map = cls_map reg = reg # landmark = landmark.cpu().data.numpy() keep_inds = (cls_map.squeeze() > self.thresh[1]).nonzero().squeeze() if keep_inds.dim() > 0 and len(keep_inds) > 0: boxes = dets[keep_inds] _cls = cls_map[keep_inds] reg = reg[keep_inds] # landmark = landmark[keep_inds] else: return None, None keep = utils.nms(boxes, 0.7) if len(keep) == 0: return None, None keep_cls = _cls[keep] keep_boxes = boxes[keep] keep_reg = reg[keep] # keep_landmark = landmark[keep] bw = keep_boxes[:, 2] - keep_boxes[:, 0] + 1 bh = keep_boxes[:, 3] - keep_boxes[:, 1] + 1 boxes = torch.cat([keep_boxes[:, 0:4], keep_cls[:, 0:1]], dim=-1) align_topx = keep_boxes[:, 0] + keep_reg[:, 0] * bw align_topy = keep_boxes[:, 1] + keep_reg[:, 1] * bh align_bottomx = keep_boxes[:, 2] + keep_reg[:, 2] * bw align_bottomy = keep_boxes[:, 3] + keep_reg[:, 3] * bh boxes_align = torch.stack([ align_topx, align_topy, align_bottomx, align_bottomy, keep_cls[:, 0], ], dim=-1) return boxes, boxes_align
def detect_pnet(self, im): """Get face candidates through pnet Parameters: ---------- im: torch Tensor input image array Returns: ------- boxes: numpy array detected boxes before calibration boxes_align: numpy array boxes after calibration """ net_size = 12 current_scale = float( net_size) / self.min_face_size # find initial scale im_resized = self.resize_image(im, current_scale) _, _, current_height, current_width = im_resized.shape # fcn all_boxes = list() while min(current_height, current_width) > net_size: feed_imgs = im_resized if self.pnet_detector.use_cuda: feed_imgs = feed_imgs.cuda() cls_map, reg = self.pnet_detector(feed_imgs.float()) boxes = self.generate_bounding_box(cls_map[0, :, :], reg, current_scale, self.thresh[0]) current_scale *= self.scale_factor im_resized = self.resize_image(im, current_scale) _, _, current_height, current_width = im_resized.shape if boxes.nelement() == 0: continue keep = utils.nms(boxes[:, :5], 0.5, 'Union') boxes = boxes[keep] all_boxes.append(boxes) if len(all_boxes) == 0: return None, None all_boxes = torch.cat(all_boxes) # merge the detection from first stage keep = utils.nms(all_boxes[:, 0:5], 0.7, 'Union') all_boxes = all_boxes[keep] # boxes = all_boxes[:, :5] bw = all_boxes[:, 2] - all_boxes[:, 0] + 1 bh = all_boxes[:, 3] - all_boxes[:, 1] + 1 # landmark_keep = all_boxes[:, 9:].reshape((5,2)) boxes = all_boxes[:, :5] # boxes = boxes.t() align_topx = all_boxes[:, 0] + all_boxes[:, 5] * bw align_topy = all_boxes[:, 1] + all_boxes[:, 6] * bh align_bottomx = all_boxes[:, 2] + all_boxes[:, 7] * bw align_bottomy = all_boxes[:, 3] + all_boxes[:, 8] * bh # refine the boxes boxes_align = torch.stack([ align_topx, align_topy, align_bottomx, align_bottomy, all_boxes[:, 4], ], dim=-1) # boxes_align = boxes_align.t() return boxes, boxes_align