def decode(roi_locs, roi_scores, indices_and_rois, test_rois_num, configer, metas): indices_and_rois = indices_and_rois num_classes = configer.get('data', 'num_classes') mean = torch.Tensor(configer.get('roi', 'loc_normalize_mean')).repeat(num_classes)[None] std = torch.Tensor(configer.get('roi', 'loc_normalize_std')).repeat(num_classes)[None] mean = mean.to(roi_locs.device) std = std.to(roi_locs.device) roi_locs = (roi_locs * std + mean) roi_locs = roi_locs.contiguous().view(-1, num_classes, 4) rois = indices_and_rois[:, 1:] rois = rois.contiguous().view(-1, 1, 4).expand_as(roi_locs) wh = torch.exp(roi_locs[:, :, 2:]) * (rois[:, :, 2:] - rois[:, :, :2]) cxcy = roi_locs[:, :, :2] * (rois[:, :, 2:] - rois[:, :, :2]) + (rois[:, :, :2] + rois[:, :, 2:]) / 2 dst_bbox = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4] if configer.get('phase') != 'debug': cls_prob = F.softmax(roi_scores, dim=1) else: cls_prob = roi_scores cls_label = torch.LongTensor([i for i in range(num_classes)])\ .contiguous().view(1, num_classes).repeat(indices_and_rois.size(0), 1).to(roi_locs.device) output = [None for _ in range(test_rois_num.size(0))] start_index = 0 for i in range(test_rois_num.size(0)): tmp_dst_bbox = dst_bbox[start_index:start_index+test_rois_num[i]] tmp_dst_bbox[:, :, 0::2] = tmp_dst_bbox[:, :, 0::2].clamp(min=0, max=metas[i]['border_size'][0] - 1) tmp_dst_bbox[:, :, 1::2] = tmp_dst_bbox[:, :, 1::2].clamp(min=0, max=metas[i]['border_size'][1] - 1) tmp_dst_bbox *= (metas[i]['ori_img_size'][0] / metas[i]['border_size'][0]) tmp_cls_prob = cls_prob[start_index:start_index+test_rois_num[i]] tmp_cls_label = cls_label[start_index:start_index+test_rois_num[i]] start_index += test_rois_num[i] mask = (tmp_cls_prob > configer.get('res', 'val_conf_thre')) & (tmp_cls_label > 0) tmp_dst_bbox = tmp_dst_bbox[mask].contiguous().view(-1, 4) if tmp_dst_bbox.numel() == 0: continue tmp_cls_prob = tmp_cls_prob[mask].contiguous().view(-1,).unsqueeze(1) tmp_cls_label = tmp_cls_label[mask].contiguous().view(-1,).unsqueeze(1) valid_preds = torch.cat((tmp_dst_bbox, tmp_cls_prob.float(), tmp_cls_label.float()), 1) valid_ind = DetHelper.cls_nms(valid_preds[:, :5], labels=valid_preds[:, 5], max_threshold=configer.get('res', 'nms')['max_threshold'], return_ind=True) valid_preds = valid_preds[valid_ind] output[i] = valid_preds return output
def __call__(self, feat_list, data_dict): device = feat_list[0].device gt_bboxes = data_dict['bboxes'] gt_labels = data_dict['labels'] input_size = [data_dict['img'].size(3), data_dict['img'].size(2)] anchor_boxes = self.fr_proirbox_layer(feat_list, input_size).to(device) target_bboxes = list() target_labels = list() for i in range(len(gt_bboxes)): if gt_bboxes[i] is None or len(gt_bboxes[i]) == 0: loc = torch.zeros_like(anchor_boxes) conf = torch.zeros((anchor_boxes.size(0), )).long() else: iou = DetHelper.bbox_iou( gt_bboxes[i], torch.cat([ anchor_boxes[:, :2] - anchor_boxes[:, 2:] / 2, anchor_boxes[:, :2] + anchor_boxes[:, 2:] / 2 ], 1)) # [#obj,8732] prior_box_iou, max_idx = iou.max(0, keepdim=False) # [1,8732] boxes = gt_bboxes[i][max_idx] # [8732,4] variances = [0.1, 0.2] cxcy = (boxes[:, :2] + boxes[:, 2:]) / 2 - anchor_boxes[:, :2] # [8732,2] cxcy /= variances[0] * anchor_boxes[:, 2:] wh = (boxes[:, 2:] - boxes[:, :2]) / anchor_boxes[:, 2:] # [8732,2] wh = torch.log(wh) / variances[1] loc = torch.cat([cxcy, wh], 1) # [8732,4] conf = 1 + gt_labels[i][ max_idx] # [8732,], background class = 0 if self.configer.get('anchor', 'anchor_method') == 'retina': conf[prior_box_iou < self.configer.get( 'anchor', 'iou_threshold')] = -1 conf[prior_box_iou < self.configer.get('anchor', 'iou_threshold') - 0.1] = 0 else: conf[prior_box_iou < self.configer.get( 'anchor', 'iou_threshold')] = 0 # background # According to IOU, it give every prior box a class label. # Then if the IOU is lower than the threshold, the class label is 0(background). class_iou, prior_box_idx = iou.max(1, keepdim=False) conf_class_idx = prior_box_idx.cpu().numpy() conf[conf_class_idx] = gt_labels[i] + 1 target_bboxes.append(loc) target_labels.append(conf) return torch.stack(target_bboxes, 0), torch.stack(target_labels, 0)
def decode(bbox, conf, default_boxes, configer, input_size): loc = bbox if configer.get('phase') != 'debug': conf = F.softmax(conf, dim=-1) default_boxes = default_boxes.unsqueeze(0).repeat(loc.size(0), 1, 1).to(bbox.device) variances = [0.1, 0.2] wh = torch.exp(loc[:, :, 2:] * variances[1]) * default_boxes[:, :, 2:] cxcy = loc[:, :, :2] * variances[0] * default_boxes[:, :, 2:] + default_boxes[:, :, :2] boxes = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4] batch_size, num_priors, _ = boxes.size() boxes = boxes.unsqueeze(2).repeat(1, 1, configer.get('data', 'num_classes'), 1) boxes = boxes.contiguous().view(boxes.size(0), -1, 4) # clip bounding box boxes[:, :, 0::2] = boxes[:, :, 0::2].clamp(min=0, max=input_size[0] - 1) boxes[:, :, 1::2] = boxes[:, :, 1::2].clamp(min=0, max=input_size[1] - 1) labels = torch.Tensor([i for i in range(configer.get('data', 'num_classes'))]).to(boxes.device) labels = labels.view(1, 1, -1, 1).repeat(batch_size, num_priors, 1, 1).contiguous().view(batch_size, -1, 1) max_conf = conf.contiguous().view(batch_size, -1, 1) # max_conf, labels = conf.max(2, keepdim=True) # [b, 8732,1] predictions = torch.cat((boxes, max_conf.float(), labels.float()), 2) output = [None for _ in range(len(predictions))] for image_i, image_pred in enumerate(predictions): ids = labels[image_i].squeeze(1).nonzero().contiguous().view(-1,) if ids.numel() == 0: continue valid_preds = image_pred[ids] _, order = valid_preds[:, 4].sort(0, descending=True) order = order[:configer.get('res', 'nms')['pre_nms']] valid_preds = valid_preds[order] valid_preds = valid_preds[valid_preds[:, 4] > configer.get('res', 'val_conf_thre')] if valid_preds.numel() == 0: continue valid_preds = DetHelper.cls_nms(valid_preds[:, :6], labels=valid_preds[:, 5], max_threshold=configer.get('res', 'nms')['max_threshold'], cls_keep_num=configer.get('res', 'cls_keep_num')) _, order = valid_preds[:, 4].sort(0, descending=True) order = order[:configer.get('res', 'max_per_image')] output[image_i] = valid_preds[order] return output
def decode(batch_pred_bboxes, configer): box_corner = batch_pred_bboxes.new(batch_pred_bboxes.shape) box_corner[:, :, 0] = batch_pred_bboxes[:, :, 0] - batch_pred_bboxes[:, :, 2] / 2 box_corner[:, :, 1] = batch_pred_bboxes[:, :, 1] - batch_pred_bboxes[:, :, 3] / 2 box_corner[:, :, 2] = batch_pred_bboxes[:, :, 0] + batch_pred_bboxes[:, :, 2] / 2 box_corner[:, :, 3] = batch_pred_bboxes[:, :, 1] + batch_pred_bboxes[:, :, 3] / 2 # clip bounding box box_corner[:, :, 0::2] = box_corner[:, :, 0::2].clamp(min=0, max=1.0) box_corner[:, :, 1::2] = box_corner[:, :, 1::2].clamp(min=0, max=1.0) batch_pred_bboxes[:, :, :4] = box_corner[:, :, :4] output = [None for _ in range(len(batch_pred_bboxes))] for image_i, image_pred in enumerate(batch_pred_bboxes): # Filter out confidence scores below threshold conf_mask = (image_pred[:, 4] > configer.get( 'vis', 'obj_threshold')).squeeze() image_pred = image_pred[conf_mask] # If none are remaining => process next image if image_pred.numel() == 0: continue # Get score and class with highest confidence class_conf, class_pred = torch.max( image_pred[:, 5:5 + configer.get('data', 'num_classes')], 1, keepdim=True) # Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred) detections = torch.cat( (image_pred[:, :5], class_conf.float(), class_pred.float()), 1) keep_index = DetHelper.cls_nms( image_pred[:, :4], scores=image_pred[:, 4], labels=class_pred.squeeze(1), nms_threshold=configer.get('nms', 'max_threshold'), iou_mode=configer.get('nms', 'mode'), nms_mode='cython_nms') output[image_i] = detections[keep_index] return output
def decode(loc, conf, configer, meta): batch_size, num_priors, _ = loc.size() loc = loc.unsqueeze(2).repeat(1, 1, configer.get('data', 'num_classes'), 1) loc = loc.contiguous().view(loc.size(0), -1, 4) labels = torch.Tensor([ i for i in range(configer.get('data', 'num_classes')) ]).to(loc.device) labels = labels.view(1, 1, -1, 1).repeat(batch_size, num_priors, 1, 1).contiguous().view(batch_size, -1, 1) conf = conf.contiguous().view(batch_size, -1, 1) # max_conf, labels = conf.max(2, keepdim=True) # [b, 8732,1] predictions = torch.cat((loc.float(), conf.float(), labels.float()), 2) output = [None for _ in range(len(predictions))] for i, image_pred in enumerate(predictions): image_pred[:, 0] *= meta[i]['ori_img_size'][0] image_pred[:, 1] *= meta[i]['ori_img_size'][1] image_pred[:, 2] *= meta[i]['ori_img_size'][0] image_pred[:, 3] *= meta[i]['ori_img_size'][1] ids = labels[i].squeeze(1).nonzero().contiguous().view(-1, ) if ids.numel() == 0: continue valid_preds = image_pred[ids] _, order = valid_preds[:, 4].sort(0, descending=True) order = order[:configer.get('res', 'nms')['pre_nms']] valid_preds = valid_preds[order] valid_preds = valid_preds[ valid_preds[:, 4] > configer.get('res', 'val_conf_thre')] if valid_preds.numel() == 0: continue valid_ind = DetHelper.cls_nms( valid_preds[:, :5], labels=valid_preds[:, 5], max_threshold=configer.get('res', 'nms')['max_threshold'], cls_keep_num=configer.get('res', 'cls_keep_num'), return_ind=True) valid_preds = valid_preds[valid_ind] _, order = valid_preds[:, 4].sort(0, descending=True) order = order[:configer.get('res', 'max_per_image')] output[i] = valid_preds[order] return output
def decode(batch_detections, configer, meta): output = [None for _ in range(len(meta))] for i in range(len(meta)): image_pred = batch_detections[i] image_pred[:, 0] *= meta[i]['ori_img_size'][0] image_pred[:, 1] *= meta[i]['ori_img_size'][1] image_pred[:, 2] *= meta[i]['ori_img_size'][0] image_pred[:, 3] *= meta[i]['ori_img_size'][1] # Filter out confidence scores below threshold image_pred = image_pred[image_pred[:, 4] > configer.get('res', 'val_conf_thre')] # If none are remaining => process next image if image_pred.numel() == 0: continue # Get score and class with highest confidence class_conf, class_pred = torch.max(image_pred[:, 5:5 + configer.get('data', 'num_classes')], 1, keepdim=True) # Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred) detections = torch.cat((image_pred[:, :5], class_conf.float(), class_pred.float()), 1) valid_ind = DetHelper.cls_nms(detections[:, :5], labels=class_pred.squeeze(1), max_threshold=configer.get('res', 'nms')['max_threshold'], return_ind=True) output[i] = detections[valid_ind] return output
def __call__(self, indices_and_rois, gt_bboxes, gt_labels, meta, gt_polygons=None): n_sample = self.configer.get('roi', 'sampler')['n_sample'] pos_iou_thresh = self.configer.get('roi', 'sampler')['pos_iou_thresh'] neg_iou_thresh_hi = self.configer.get('roi', 'sampler')['neg_iou_thresh_hi'] neg_iou_thresh_lo = self.configer.get('roi', 'sampler')['neg_iou_thresh_lo'] pos_ratio = self.configer.get('roi', 'sampler')['pos_ratio'] loc_normalize_mean = self.configer.get('roi', 'loc_normalize_mean') loc_normalize_std = self.configer.get('roi', 'loc_normalize_std') sample_roi_list = list() gt_roi_loc_list = list() gt_roi_label_list= list() gt_roi_mask_list = list() for i in range(len(gt_bboxes)): temp_gt_bboxes = gt_bboxes[i].to(indices_and_rois.device) temp_gt_labels = gt_labels[i].to(indices_and_rois.device) if temp_gt_bboxes.numel() == 0: min_size = self.configer.get('rpn', 'min_size') roi_size = random.randint(min_size, min(meta[i]['border_size'])) sample_roi = torch.zeros((1, 4), requires_grad=True).float().to(indices_and_rois.device) sample_roi[0, 2:] = roi_size gt_roi_loc = torch.zeros((1, 4), requires_grad=True).float().to(sample_roi.device) gt_roi_label = torch.ones((1,), requires_grad=True).long().to(sample_roi.device).mul_(-1) else: pos_roi_per_image = np.round(n_sample * pos_ratio) if self.configer.get('phase') == 'debug': rois = indices_and_rois[indices_and_rois[:, 0] == i][:, 1:] else: if indices_and_rois.numel() == 0: rois = temp_gt_bboxes else: rois = torch.cat((indices_and_rois[indices_and_rois[:, 0] == i][:, 1:], temp_gt_bboxes), 0) iou = DetHelper.bbox_iou(rois, temp_gt_bboxes) max_iou, gt_assignment = iou.max(1, keepdim=False) # Offset range of classes from [0, n_fg_class - 1] to [1, n_fg_class]. # The label with value 0 is the background. gt_roi_label = temp_gt_labels[gt_assignment] + 1 max_iou = max_iou.cpu().detach().numpy() # Select foreground RoIs as those with >= pos_iou_thresh IoU. pos_index = np.where(max_iou >= pos_iou_thresh)[0] pos_roi_per_this_image = int(min(pos_roi_per_image, pos_index.size)) if pos_index.size > 0: pos_index = np.random.choice(pos_index, size=pos_roi_per_this_image, replace=False) # Select background RoIs as those within # [neg_iou_thresh_lo, neg_iou_thresh_hi). neg_index = np.where((max_iou < neg_iou_thresh_hi) & (max_iou >= neg_iou_thresh_lo))[0] neg_roi_per_this_image = n_sample - pos_roi_per_this_image neg_roi_per_this_image = int(min(neg_roi_per_this_image, neg_index.size)) if neg_index.size > 0: neg_index = np.random.choice(neg_index, size=neg_roi_per_this_image, replace=False) # The indices that we're selecting (both positive and negative). keep_index = np.append(pos_index, neg_index) gt_roi_label = gt_roi_label[keep_index].detach() gt_roi_label[pos_roi_per_this_image:] = 0 # negative labels --> 0 sample_roi = rois[keep_index].detach() if gt_polygons is not None: temp_gt_polygons = gt_polygons[i] target_size = [self.configer.get('roi', 'pooled_width'), self.configer.get('roi', 'pooled_height')] for roi_index in range(pos_roi_per_this_image): gt_index = gt_assignment[keep_index[roi_index]] roi_polygons = temp_gt_polygons[gt_index] roi = sample_roi[roi_index].cpu().numpy() mask = MaskHelper.polys2mask_wrt_box(roi_polygons, roi, target_size) mask = torch.from_numpy(mask).to(indices_and_rois.device) gt_roi_mask_list.append(mask) # Compute offsets and scales to match sampled RoIs to the GTs. boxes = temp_gt_bboxes[gt_assignment][keep_index] cxcy = (boxes[:, :2] + boxes[:, 2:]) / 2 - (sample_roi[:, :2] + sample_roi[:, 2:]) / 2 # [8732,2] cxcy /= (sample_roi[:, 2:] - sample_roi[:, :2]) wh = (boxes[:, 2:] - boxes[:, :2]) / (sample_roi[:, 2:] - sample_roi[:, :2]) # [8732,2] wh = torch.log(wh) loc = torch.cat([cxcy, wh], 1).detach() # [8732,4] # loc = loc[:, [1, 0, 3, 2]] normalize_mean = torch.Tensor(loc_normalize_mean).to(loc.device) normalize_std = torch.Tensor(loc_normalize_std).to(loc.device) gt_roi_loc = (loc - normalize_mean) / normalize_std batch_index = i * torch.ones((len(sample_roi),)).to(sample_roi.device) sample_roi = torch.cat([batch_index[:, None], sample_roi], dim=1).contiguous() sample_roi_list.append(sample_roi) gt_roi_loc_list.append(gt_roi_loc) gt_roi_label_list.append(gt_roi_label) # sample_roi.register_hook(lambda g: print(g)) sample_roi = torch.cat(sample_roi_list, 0) gt_roi_loc = torch.cat(gt_roi_loc_list, 0) gt_roi_label = torch.cat(gt_roi_label_list, 0) if gt_polygons is not None: gt_pos_roi_mask = torch.cat(gt_roi_mask_list, 0) return sample_roi, gt_roi_loc, gt_roi_label, gt_pos_roi_mask else: return sample_roi, gt_roi_loc, gt_roi_label
def __call__(self, feat_list, gt_bboxes, meta): anchor_boxes = self.fr_proirbox_layer(feat_list, meta[0]['input_size']) n_sample = self.configer.get('rpn', 'loss')['n_sample'] pos_iou_thresh = self.configer.get('rpn', 'loss')['pos_iou_thresh'] neg_iou_thresh = self.configer.get('rpn', 'loss')['neg_iou_thresh'] pos_ratio = self.configer.get('rpn', 'loss')['pos_ratio'] # Calc indicies of anchors which are located completely inside of the image # whose size is speficied. target_bboxes = list() target_labels = list() for i in range(len(gt_bboxes)): index_inside = ( ((anchor_boxes[:, 0] - anchor_boxes[:, 2] / 2) >= 0) & ((anchor_boxes[:, 1] - anchor_boxes[:, 3] / 2) >= 0) & ((anchor_boxes[:, 0] + anchor_boxes[:, 2] / 2) < meta[i]['border_size'][0]) & ((anchor_boxes[:, 1] + anchor_boxes[:, 3] / 2) < meta[i]['border_size'][1])) index_inside = index_inside.nonzero().contiguous().view(-1, ) default_boxes = anchor_boxes[index_inside] loc = torch.zeros_like(default_boxes) label = torch.ones((default_boxes.size(0), )).mul_(-1).long() if gt_bboxes[i].numel() > 0: # label: 1 is positive, 0 is negative, -1 is dont care ious = DetHelper.bbox_iou( gt_bboxes[i], torch.cat([ default_boxes[:, :2] - default_boxes[:, 2:] / 2, default_boxes[:, :2] + default_boxes[:, 2:] / 2 ], 1)) max_ious, argmax_ious = ious.max(0, keepdim=False) _, gt_argmax_ious = ious.max(1, keepdim=False) # assign negative labels first so that positive labels can clobber them label[max_ious < neg_iou_thresh] = 0 # positive label: for each gt, anchor with highest iou label[gt_argmax_ious] = 1 # positive label: above threshold IOU label[max_ious >= pos_iou_thresh] = 1 # subsample positive labels if we have too many n_pos = int(pos_ratio * n_sample) pos_index = (label == 1).nonzero().contiguous().view( -1, ).numpy() if len(pos_index) > n_pos: disable_index = np.random.choice(pos_index, size=(len(pos_index) - n_pos), replace=False) label[disable_index] = -1 # subsample negative labels if we have too many n_neg = n_sample - torch.sum(label == 1).item() neg_index = (label == 0).nonzero().contiguous().view( -1, ).numpy() if len(neg_index) > n_neg: disable_index = np.random.choice(neg_index, size=(len(neg_index) - n_neg), replace=False) label[disable_index] = -1 boxes = gt_bboxes[i][argmax_ious] # [8732,4] cxcy = (boxes[:, :2] + boxes[:, 2:]) / 2 - default_boxes[:, :2] # [8732,2] cxcy /= default_boxes[:, 2:] wh = (boxes[:, 2:] - boxes[:, :2]) / default_boxes[:, 2:] # [8732,2] wh = torch.log(wh) loc = torch.cat([cxcy, wh], 1) # [8732,4] # loc = loc[:, [1, 0, 3, 2]] else: # subsample negative labels if we have too many n_neg = n_sample // 2 neg_index = (label == -1).nonzero().contiguous().view( -1, ).numpy() if len(neg_index) > n_neg: disable_index = np.random.choice(neg_index, size=n_neg, replace=False) label[disable_index] = 0 ret_label = torch.ones((anchor_boxes.size(0), ), dtype=torch.long).mul_(-1) ret_label[index_inside] = torch.LongTensor(label) ret_loc = torch.zeros((anchor_boxes.size(0), 4)) ret_loc[index_inside] = loc target_bboxes.append(ret_loc) target_labels.append(ret_label) return torch.stack(target_bboxes, 0), torch.stack(target_labels, 0)
def __call__(self, feat_list, batch_gt_bboxes, batch_gt_labels, input_size): batch_target_list = list() batch_objmask_list = list() batch_noobjmask_list = list() for i, ori_anchors in enumerate(self.configer.get( 'gt', 'anchors_list')): in_h, in_w = feat_list[i].size()[2:] w_fm_stride, h_fm_stride = input_size[0] / in_w, input_size[ 1] / in_h anchors = [(a_w / w_fm_stride, a_h / h_fm_stride) for a_w, a_h in ori_anchors] batch_size = len(batch_gt_bboxes) num_anchors = len(anchors) obj_mask = torch.zeros(batch_size, num_anchors, in_h, in_w) noobj_mask = torch.ones(batch_size, num_anchors, in_h, in_w) tx = torch.zeros(batch_size, num_anchors, in_h, in_w) ty = torch.zeros(batch_size, num_anchors, in_h, in_w) tw = torch.zeros(batch_size, num_anchors, in_h, in_w) th = torch.zeros(batch_size, num_anchors, in_h, in_w) tconf = torch.zeros(batch_size, num_anchors, in_h, in_w) tcls = torch.zeros(batch_size, num_anchors, in_h, in_w, self.configer.get('data', 'num_classes')) for b in range(batch_size): for t in range(batch_gt_bboxes[b].size(0)): # Convert to position relative to box gx = (batch_gt_bboxes[b][t, 0] + batch_gt_bboxes[b][t, 2] ) / (2.0 * input_size[0]) * in_w gy = (batch_gt_bboxes[b][t, 1] + batch_gt_bboxes[b][t, 3] ) / (2.0 * input_size[1]) * in_h gw = (batch_gt_bboxes[b][t, 2] - batch_gt_bboxes[b][t, 0]) / input_size[0] * in_w gh = (batch_gt_bboxes[b][t, 3] - batch_gt_bboxes[b][t, 1]) / input_size[1] * in_h if gw * gh == 0 or gx >= in_w or gy >= in_h: continue # Get grid box indices gi = int(gx) gj = int(gy) # Get shape of gt box gt_box = torch.FloatTensor(np.array([0, 0, gw, gh])).unsqueeze(0) # Get shape of anchor box anchor_shapes = torch.FloatTensor( np.concatenate((np.zeros( (num_anchors, 2)), np.array(anchors)), 1)) # Calculate iou between gt and anchor shapes anch_ious = DetHelper.bbox_iou(gt_box, anchor_shapes) # Where the overlap is larger than threshold set mask to zero (ignore) noobj_mask[b, anch_ious[0] > self.configer. get('gt', 'iou_threshold')] = 0 # Find the best matching anchor box best_n = np.argmax(anch_ious, axis=1) # Masks obj_mask[b, best_n, gj, gi] = 1 # Coordinates tx[b, best_n, gj, gi] = gx - gi ty[b, best_n, gj, gi] = gy - gj # Width and height tw[b, best_n, gj, gi] = math.log(gw / anchors[best_n][0] + 1e-16) th[b, best_n, gj, gi] = math.log(gh / anchors[best_n][1] + 1e-16) # object tconf[b, best_n, gj, gi] = 1 # One-hot encoding of label tcls[b, best_n, gj, gi, int(batch_gt_labels[b][t])] = 1 obj_mask = obj_mask.view(batch_size, -1) noobj_mask = noobj_mask.view(batch_size, -1) tx = tx.view(batch_size, -1).unsqueeze(2) ty = ty.view(batch_size, -1).unsqueeze(2) tw = tw.view(batch_size, -1).unsqueeze(2) th = th.view(batch_size, -1).unsqueeze(2) tconf = tconf.view(batch_size, -1).unsqueeze(2) tcls = tcls.view(batch_size, -1, self.configer.get('data', 'num_classes')) target = torch.cat((tx, ty, tw, th, tconf, tcls), -1) batch_target_list.append(target) batch_objmask_list.append(obj_mask) batch_noobjmask_list.append(noobj_mask) batch_target = torch.cat(batch_target_list, 1) batch_objmask = torch.cat(batch_objmask_list, 1) batch_noobjmask = torch.cat(batch_noobjmask_list, 1) return batch_target, batch_objmask, batch_noobjmask
def decode(roi_locs, roi_scores, indices_and_rois, test_rois_num, configer, input_size): roi_locs = roi_locs.cpu() roi_scores = roi_scores.cpu() indices_and_rois = indices_and_rois.cpu() num_classes = configer.get('data', 'num_classes') mean = torch.Tensor(configer.get( 'roi', 'loc_normalize_mean')).repeat(num_classes)[None] std = torch.Tensor(configer.get( 'roi', 'loc_normalize_std')).repeat(num_classes)[None] mean = mean.to(roi_locs.device) std = std.to(roi_locs.device) roi_locs = (roi_locs * std + mean) roi_locs = roi_locs.contiguous().view(-1, num_classes, 4) # roi_locs = roi_locs[:,:, [1, 0, 3, 2]] rois = indices_and_rois[:, 1:] rois = rois.contiguous().view(-1, 1, 4).expand_as(roi_locs) wh = torch.exp(roi_locs[:, :, 2:]) * (rois[:, :, 2:] - rois[:, :, :2]) cxcy = roi_locs[:, :, :2] * (rois[:, :, 2:] - rois[:, :, :2]) + ( rois[:, :, :2] + rois[:, :, 2:]) / 2 dst_bbox = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4] # clip bounding box dst_bbox[:, :, 0::2] = (dst_bbox[:, :, 0::2]).clamp(min=0, max=input_size[0] - 1) dst_bbox[:, :, 1::2] = (dst_bbox[:, :, 1::2]).clamp(min=0, max=input_size[1] - 1) if configer.get('phase') != 'debug': cls_prob = F.softmax(roi_scores, dim=1) else: cls_prob = roi_scores cls_label = torch.LongTensor([i for i in range(num_classes)])\ .contiguous().view(1, num_classes).repeat(indices_and_rois.size(0), 1) output = [None for _ in range(test_rois_num.size(0))] start_index = 0 for i in range(test_rois_num.size(0)): # batch_index = (indices_and_rois[:, 0] == i).nonzero().contiguous().view(-1,) # tmp_dst_bbox = dst_bbox[batch_index] # tmp_cls_prob = cls_prob[batch_index] # tmp_cls_label = cls_label[batch_index] tmp_dst_bbox = dst_bbox[start_index:start_index + test_rois_num[i]] tmp_cls_prob = cls_prob[start_index:start_index + test_rois_num[i]] tmp_cls_label = cls_label[start_index:start_index + test_rois_num[i]] start_index += test_rois_num[i] mask = (tmp_cls_prob > configer.get( 'vis', 'conf_threshold')) & (tmp_cls_label > 0) tmp_dst_bbox = tmp_dst_bbox[mask].contiguous().view(-1, 4) if tmp_dst_bbox.numel() == 0: continue tmp_cls_prob = tmp_cls_prob[mask].contiguous().view( -1, ).unsqueeze(1) tmp_cls_label = tmp_cls_label[mask].contiguous().view( -1, ).unsqueeze(1) valid_preds = torch.cat( (tmp_dst_bbox, tmp_cls_prob.float(), tmp_cls_label.float()), 1) keep = DetHelper.cls_nms(valid_preds[:, :4], scores=valid_preds[:, 4], labels=valid_preds[:, 5], nms_threshold=configer.get( 'nms', 'overlap_threshold'), iou_mode=configer.get('nms', 'mode')) output[i] = valid_preds[keep] return output
def ssd_batch_encode(self, gt_bboxes, gt_labels, default_boxes): """Transform target bounding boxes and class labels to SSD boxes and classes. Match each object box to all the default boxes, pick the ones with the Jaccard-Index > threshold: Jaccard(A,B) = AB / (A+B-AB) Args: boxes(tensor): object bounding boxes (xmin,ymin,xmax,ymax) of a image, sized [#obj, 4]. classes(tensor): object class labels of a image, sized [#obj,]. threshold(float): Jaccard index threshold Returns: boxes(tensor): bounding boxes, sized [#obj, 8732, 4]. classes(tensor): class labels, sized [8732,] """ target_bboxes = list() target_labels = list() for i in range(len(gt_bboxes)): if gt_bboxes[i] is None or len(gt_bboxes[i]) == 0: loc = torch.zeros_like(default_boxes) conf = torch.zeros((default_boxes.size(0), )).long() else: iou = DetHelper.bbox_iou( gt_bboxes[i], torch.cat([ default_boxes[:, :2] - default_boxes[:, 2:] / 2, default_boxes[:, :2] + default_boxes[:, 2:] / 2 ], 1)) # [#obj,8732] prior_box_iou, max_idx = iou.max(0, keepdim=False) # [1,8732] boxes = gt_bboxes[i][max_idx] # [8732,4] variances = [0.1, 0.2] cxcy = (boxes[:, :2] + boxes[:, 2:]) / 2 - default_boxes[:, :2] # [8732,2] cxcy /= variances[0] * default_boxes[:, 2:] wh = (boxes[:, 2:] - boxes[:, :2]) / default_boxes[:, 2:] # [8732,2] wh = torch.log(wh) / variances[1] loc = torch.cat([cxcy, wh], 1) # [8732,4] conf = 1 + gt_labels[i][ max_idx] # [8732,], background class = 0 if self.configer.get('gt', 'anchor_method') == 'retina': conf[prior_box_iou < self.configer.get( 'gt', 'iou_threshold')] = -1 conf[prior_box_iou < self.configer.get('gt', 'iou_threshold') - 0.1] = 0 else: conf[prior_box_iou < self.configer.get( 'gt', 'iou_threshold')] = 0 # background # According to IOU, it give every prior box a class label. # Then if the IOU is lower than the threshold, the class label is 0(background). class_iou, prior_box_idx = iou.max(1, keepdim=False) conf_class_idx = prior_box_idx.cpu().numpy() conf[conf_class_idx] = gt_labels[i] + 1 target_bboxes.append(loc) target_labels.append(conf) return torch.stack(target_bboxes, 0), torch.stack(target_labels, 0)
def roi_batch_encode(self, gt_bboxes, gt_labels, indices_and_rois): n_sample = self.configer.get('roi', 'loss')['n_sample'] pos_iou_thresh = self.configer.get('roi', 'loss')['pos_iou_thresh'] neg_iou_thresh_hi = self.configer.get('roi', 'loss')['neg_iou_thresh_hi'] neg_iou_thresh_lo = self.configer.get('roi', 'loss')['neg_iou_thresh_lo'] pos_ratio = self.configer.get('roi', 'loss')['pos_ratio'] loc_normalize_mean = self.configer.get('roi', 'loc_normalize_mean') loc_normalize_std = self.configer.get('roi', 'loc_normalize_std') sample_roi_list = list() gt_roi_loc_list = list() gt_roi_label_list = list() for i in range(len(gt_bboxes)): rois = torch.cat( (indices_and_rois[indices_and_rois[:, 0] == i][:, :4], gt_bboxes[i]), 0) pos_roi_per_image = np.round(n_sample * pos_ratio) iou = DetHelper.bbox_iou(rois, gt_bboxes[i]) max_iou, gt_assignment = iou.max(1, keepdim=False) # Offset range of classes from [0, n_fg_class - 1] to [1, n_fg_class]. # The label with value 0 is the background. gt_roi_label = gt_labels[i][gt_assignment] + 1 max_iou = max_iou.cpu().detach().numpy() # Select foreground RoIs as those with >= pos_iou_thresh IoU. pos_index = np.where(max_iou >= pos_iou_thresh)[0] pos_roi_per_this_image = int(min(pos_roi_per_image, pos_index.size)) if pos_index.size > 0: pos_index = np.random.choice(pos_index, size=pos_roi_per_this_image, replace=False) # Select background RoIs as those within # [neg_iou_thresh_lo, neg_iou_thresh_hi). neg_index = np.where((max_iou < neg_iou_thresh_hi) & (max_iou >= neg_iou_thresh_lo))[0] neg_roi_per_this_image = n_sample - pos_roi_per_this_image neg_roi_per_this_image = int( min(neg_roi_per_this_image, neg_index.size)) if neg_index.size > 0: neg_index = np.random.choice(neg_index, size=neg_roi_per_this_image, replace=False) # The indices that we're selecting (both positive and negative). keep_index = np.append(pos_index, neg_index) gt_roi_label = gt_roi_label[keep_index] gt_roi_label[pos_roi_per_this_image:] = 0 # negative labels --> 0 sample_roi = rois[keep_index] # Compute offsets and scales to match sampled RoIs to the GTs. boxes = gt_bboxes[i][gt_assignment][keep_index] cxcy = (boxes[:, :2] + boxes[:, 2:]) / 2 - ( sample_roi[:, :2] + sample_roi[:, 2:]) / 2 # [8732,2] cxcy /= (sample_roi[:, 2:] - sample_roi[:, :2]) wh = (boxes[:, 2:] - boxes[:, :2]) / ( sample_roi[:, 2:] - sample_roi[:, :2]) # [8732,2] wh = torch.log(wh) loc = torch.cat([cxcy, wh], 1) # [8732,4] gt_roi_loc = ((loc - torch.Tensor(loc_normalize_mean)) / torch.Tensor(loc_normalize_std)) batch_index = i * torch.ones((len(sample_roi), )) sample_roi = torch.cat([batch_index[:, None], sample_roi], dim=1).contiguous() sample_roi_list.append(sample_roi) gt_roi_loc_list.append(gt_roi_loc) gt_roi_label_list.append(gt_roi_label) return torch.cat(sample_roi_list, 0), torch.cat(gt_roi_loc_list, 0), torch.cat(gt_roi_label_list, 0)