def forward_for_single_feature_map(self, anchors, objectness, box_regression): """ Arguments: anchors: list[BoxList] objectness: tensor of size N, A, H, W box_regression: tensor of size N, A * 4, H, W """ device = objectness.device N, A, H, W = objectness.shape # put in the same format as anchors objectness = permute_and_flatten(objectness, N, A, 1, H, W).view(N, -1) objectness = objectness.sigmoid() box_regression = permute_and_flatten(box_regression, N, A, 4, H, W) num_anchors = A * H * W pre_nms_top_n = min(self.pre_nms_top_n, num_anchors) objectness, topk_idx = objectness.topk(pre_nms_top_n, dim=1, sorted=True) batch_idx = torch.arange(N, device=device)[:, None] box_regression = box_regression[batch_idx, topk_idx] image_shapes = [box.size for box in anchors] concat_anchors = torch.cat([a.bbox for a in anchors], dim=0) concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx] proposals = self.box_coder.decode(box_regression.view(-1, 4), concat_anchors.view(-1, 4)) proposals = proposals.view(N, -1, 4) result = [] for proposal, score, im_shape in zip(proposals, objectness, image_shapes): boxlist = BoxList(proposal, im_shape, mode="xyxy") boxlist.add_field("objectness", score) boxlist = boxlist.clip_to_image(remove_empty=False) boxlist = remove_small_boxes(boxlist, self.min_size) boxlist = boxlist_nms( boxlist, self.nms_thresh, max_proposals=self.post_nms_top_n, score_field="objectness", ) result.append(boxlist) return result
def prepare_boxlist(self, boxes, scores, image_shape): """ Returns BoxList from `boxes` and adds probability scores information as an extra field `boxes` has shape (#detections, 4 * #classes), where each row represents a list of predicted bounding boxes for each of the object classes in the dataset (including the background class). The detections in each row originate from the same object proposal. `scores` has shape (#detection, #classes), where each row represents a list of object detection confidence scores for each of the object classes in the dataset (including the background class). `scores[i, j]`` corresponds to the box at `boxes[i, j * 4:(j + 1) * 4]`. """ boxes = boxes.reshape(-1, 4) scores = scores.reshape(-1) boxlist = BoxList(boxes, image_shape, mode="xyxy") boxlist.add_field("scores", scores) return boxlist
def __getitem__(self, item): img = Image.open(self.image_lists[item]).convert("RGB") # dummy target w, h = img.size target = BoxList([[0, 0, w, h]], img.size, mode="xyxy") if self.transforms is not None: img, target = self.transforms(img, target) return img, target
def forward(self, image_list, feature_maps): grid_sizes = [feature_map.shape[-2:] for feature_map in feature_maps] anchors_over_all_feature_maps = self.grid_anchors(grid_sizes) anchors = [] for i, (image_height, image_width) in enumerate(image_list.image_sizes): anchors_in_image = [] for anchors_per_feature_map in anchors_over_all_feature_maps: boxlist = BoxList( anchors_per_feature_map, (image_width, image_height), mode="xyxy" ) self.add_visibility_to(boxlist) anchors_in_image.append(boxlist) anchors.append(anchors_in_image) return anchors
def __getitem__(self, idx): img, anno = super(COCODataset, self).__getitem__(idx) # filter crowd annotations # TODO might be better to add an extra field anno = [obj for obj in anno if obj["iscrowd"] == 0] boxes = [obj["bbox"] for obj in anno] boxes = torch.as_tensor(boxes).reshape(-1, 4) # guard against no boxes target = BoxList(boxes, img.size, mode="xywh").convert("xyxy") classes = [obj["category_id"] for obj in anno] classes = [self.json_category_id_to_contiguous_id[c] for c in classes] classes = torch.tensor(classes) target.add_field("labels", classes) if anno: valid_masks = [] masks = [] for obj in anno: valid_masks.append("segmentation" in obj) masks.append( obj.get( "segmentation", [[0, 0, 0, img.size[1], img.size[0], img.size[1]]])) masks = SegmentationMask(masks, img.size, mode='poly') valid_masks = torch.tensor(valid_masks) target.add_field("masks", masks) target.add_field("valid_masks", valid_masks) target = target.clip_to_image(remove_empty=True) if self._transforms is not None: img, target = self._transforms(img, target) return img, target, idx
def select_over_all_levels(self, boxlists): num_images = len(boxlists) results = [] for i in range(num_images): scores = boxlists[i].get_field("scores") labels = boxlists[i].get_field("labels") boxes = boxlists[i].bbox boxlist = boxlists[i] result = [] # skip the background for j in range(1, self.num_classes): inds = (labels == j).nonzero().view(-1) scores_j = scores[inds] boxes_j = boxes[inds, :].view(-1, 4) boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy") boxlist_for_class.add_field("scores", scores_j) boxlist_for_class = boxlist_nms(boxlist_for_class, self.nms_thresh, score_field="scores") num_labels = len(boxlist_for_class) boxlist_for_class.add_field( "labels", torch.full((num_labels, ), j, dtype=torch.int64, device=scores.device)) result.append(boxlist_for_class) result = cat_boxlist(result) number_of_detections = len(result) # Limit to max_per_image detections **over all classes** if number_of_detections > self.fpn_post_nms_top_n > 0: cls_scores = result.get_field("scores") image_thresh, _ = torch.kthvalue( cls_scores.cpu(), number_of_detections - self.fpn_post_nms_top_n + 1) keep = cls_scores >= image_thresh.item() keep = torch.nonzero(keep).squeeze(1) result = result[keep] results.append(result) return results
def filter_results(self, boxlist, num_classes): """Returns bounding-box detection results by thresholding on scores and applying non-maximum suppression (NMS). """ # unwrap the boxlist to avoid additional overhead. # if we had multi-class NMS, we could perform this directly on the boxlist boxes = boxlist.bbox.reshape(-1, num_classes * 4) scores = boxlist.get_field("scores").reshape(-1, num_classes) device = scores.device result = [] # Apply threshold on detection probabilities and apply NMS # Skip j = 0, because it's the background class inds_all = scores > self.score_thresh for j in range(1, num_classes): inds = inds_all[:, j].nonzero().squeeze(1) scores_j = scores[inds, j] boxes_j = boxes[inds, j * 4:(j + 1) * 4] boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy") boxlist_for_class.add_field("scores", scores_j) boxlist_for_class = boxlist_nms(boxlist_for_class, self.nms) num_labels = len(boxlist_for_class) boxlist_for_class.add_field( "labels", torch.full((num_labels, ), j, dtype=torch.int64, device=device)) result.append(boxlist_for_class) result = cat_boxlist(result) number_of_detections = len(result) # Limit to max_per_image detections **over all classes** if number_of_detections > self.detections_per_img > 0: cls_scores = result.get_field("scores") image_thresh, _ = torch.kthvalue( cls_scores.cpu(), number_of_detections - self.detections_per_img + 1) keep = cls_scores >= image_thresh.item() keep = torch.nonzero(keep).squeeze(1) result = result[keep] return result
def forward(self, x, boxes): """ Arguments: x (Tensor): the mask logits boxes (list[BoxList]): bounding boxes that are used as reference, one for ech image Returns: results (list[BoxList]): one BoxList for each image, containing the extra field mask """ mask_prob = x.sigmoid() # select masks coresponding to the predicted classes num_masks = x.shape[0] labels = [bbox.get_field("labels") for bbox in boxes] labels = torch.cat(labels) index = torch.arange(num_masks, device=labels.device) if not self.cfg.MODEL.ROI_MASK_HEAD.CLASS_AGNOSTIC: mask_prob = mask_prob[index, labels][:, None] boxes_per_image = [len(box) for box in boxes] mask_prob = mask_prob.split(boxes_per_image, dim=0) if self.masker: mask_prob = self.masker(mask_prob, boxes) results = [] for prob, box in zip(mask_prob, boxes): bbox = BoxList(box.bbox, box.size, mode="xyxy") for field in box.fields(): bbox.add_field(field, box.get_field(field)) bbox.add_field("mask", prob) results.append(bbox) return results
def evaluate_box_proposals(predictions, dataset, thresholds=None, area="all", limit=None): """Evaluate detection proposal recall metrics. This function is a much faster alternative to the official COCO API recall evaluation code. However, it produces slightly different results. """ # Record max overlap value for each gt box # Return vector of overlap values areas = { "all": 0, "small": 1, "medium": 2, "large": 3, "96-128": 4, "128-256": 5, "256-512": 6, "512-inf": 7, } area_ranges = [ [0**2, 1e5**2], # all [0**2, 32**2], # small [32**2, 96**2], # medium [96**2, 1e5**2], # large [96**2, 128**2], # 96-128 [128**2, 256**2], # 128-256 [256**2, 512**2], # 256-512 [512**2, 1e5**2], ] # 512-inf assert area in areas, "Unknown area range: {}".format(area) area_range = area_ranges[areas[area]] gt_overlaps = [] num_pos = 0 for image_id, prediction in enumerate(predictions): original_id = dataset.id_to_img_map[image_id] img_info = dataset.get_img_info(image_id) image_width = img_info["width"] image_height = img_info["height"] prediction = prediction.resize((image_width, image_height)) # sort predictions in descending order # TODO maybe remove this and make it explicit in the documentation inds = prediction.get_field("objectness").sort(descending=True)[1] prediction = prediction[inds] ann_ids = dataset.coco.getAnnIds(imgIds=original_id) anno = dataset.coco.loadAnns(ann_ids) gt_boxes = [obj["bbox"] for obj in anno if obj["iscrowd"] == 0] gt_boxes = torch.as_tensor(gt_boxes).reshape( -1, 4) # guard against no boxes gt_boxes = BoxList(gt_boxes, (image_width, image_height), mode="xywh").convert("xyxy") gt_areas = torch.as_tensor( [obj["area"] for obj in anno if obj["iscrowd"] == 0]) if len(gt_boxes) == 0: continue valid_gt_inds = (gt_areas >= area_range[0]) & (gt_areas <= area_range[1]) gt_boxes = gt_boxes[valid_gt_inds] num_pos += len(gt_boxes) if len(gt_boxes) == 0: continue if len(prediction) == 0: continue if limit is not None and len(prediction) > limit: prediction = prediction[:limit] overlaps = boxlist_iou(prediction, gt_boxes) _gt_overlaps = torch.zeros(len(gt_boxes)) for j in range(min(len(prediction), len(gt_boxes))): # find which proposal box maximally covers each gt box # and get the iou amount of coverage for each gt box max_overlaps, argmax_overlaps = overlaps.max(dim=0) # find which gt box is 'best' covered (i.e. 'best' = most iou) gt_ovr, gt_ind = max_overlaps.max(dim=0) assert gt_ovr >= 0 # find the proposal box that covers the best covered gt box box_ind = argmax_overlaps[gt_ind] # record the iou coverage of this gt box _gt_overlaps[j] = overlaps[box_ind, gt_ind] assert _gt_overlaps[j] == gt_ovr # mark the proposal box and the gt box as used overlaps[box_ind, :] = -1 overlaps[:, gt_ind] = -1 # append recorded iou coverage level gt_overlaps.append(_gt_overlaps) gt_overlaps = torch.cat(gt_overlaps, dim=0) gt_overlaps, _ = torch.sort(gt_overlaps) if thresholds is None: step = 0.05 thresholds = torch.arange(0.5, 0.95 + 1e-5, step, dtype=torch.float32) recalls = torch.zeros_like(thresholds) # compute recall for each iou threshold for i, t in enumerate(thresholds): recalls[i] = (gt_overlaps >= t).float().sum() / float(num_pos) # ar = 2 * np.trapz(recalls, thresholds) ar = recalls.mean() return { "ar": ar, "recalls": recalls, "thresholds": thresholds, "gt_overlaps": gt_overlaps, "num_pos": num_pos, }
def im_detect_bbox_aug(model, images, device): # Collect detections computed under different transformations boxlists_ts = [] for _ in range(len(images)): boxlists_ts.append([]) def add_preds_t(boxlists_t): for i, boxlist_t in enumerate(boxlists_t): if len(boxlists_ts[i]) == 0: # The first one is identity transform, no need to resize the boxlist boxlists_ts[i].append(boxlist_t) else: # Resize the boxlist as the first one boxlists_ts[i].append(boxlist_t.resize(boxlists_ts[i][0].size)) # Compute detections for the original image (identity transform) boxlists_i = im_detect_bbox(model, images, cfg.INPUT.MIN_SIZE_TEST, cfg.INPUT.MAX_SIZE_TEST, device) add_preds_t(boxlists_i) # Perform detection on the horizontally flipped image if cfg.TEST.BBOX_AUG.H_FLIP: boxlists_hf = im_detect_bbox_hflip(model, images, cfg.INPUT.MIN_SIZE_TEST, cfg.INPUT.MAX_SIZE_TEST, device) add_preds_t(boxlists_hf) # Compute detections at different scales for scale in cfg.TEST.BBOX_AUG.SCALES: max_size = cfg.TEST.BBOX_AUG.MAX_SIZE boxlists_scl = im_detect_bbox_scale(model, images, scale, max_size, device) add_preds_t(boxlists_scl) if cfg.TEST.BBOX_AUG.SCALE_H_FLIP: boxlists_scl_hf = im_detect_bbox_scale(model, images, scale, max_size, device, hflip=True) add_preds_t(boxlists_scl_hf) # Merge boxlists detected by different bbox aug params boxlists = [] for i, boxlist_ts in enumerate(boxlists_ts): bbox = torch.cat([boxlist_t.bbox for boxlist_t in boxlist_ts]) scores = torch.cat( [boxlist_t.get_field('scores') for boxlist_t in boxlist_ts]) boxlist = BoxList(bbox, boxlist_ts[0].size, boxlist_ts[0].mode) boxlist.add_field('scores', scores) boxlists.append(boxlist) # Apply NMS and limit the final detections results = [] post_processor = make_roi_box_post_processor(cfg) for boxlist in boxlists: results.append( post_processor.filter_results(boxlist, cfg.MODEL.ROI_BOX_HEAD.NUM_CLASSES)) return results
def forward_for_single_feature_map(self, anchors, box_cls, box_regression): """ Arguments: anchors: list[BoxList] box_cls: tensor of size N, A * C, H, W box_regression: tensor of size N, A * 4, H, W """ device = box_cls.device N, _, H, W = box_cls.shape A = box_regression.size(1) // 4 C = box_cls.size(1) // A # put in the same format as anchors box_cls = permute_and_flatten(box_cls, N, A, C, H, W) box_cls = box_cls.sigmoid() box_regression = permute_and_flatten(box_regression, N, A, 4, H, W) box_regression = box_regression.reshape(N, -1, 4) num_anchors = A * H * W candidate_inds = box_cls > self.pre_nms_thresh pre_nms_top_n = candidate_inds.view(N, -1).sum(1) pre_nms_top_n = pre_nms_top_n.clamp(max=self.pre_nms_top_n) results = [] for per_box_cls, per_box_regression, per_pre_nms_top_n, \ per_candidate_inds, per_anchors in zip( box_cls, box_regression, pre_nms_top_n, candidate_inds, anchors): # Sort and select TopN # TODO most of this can be made out of the loop for # all images. # TODO:Yang: Not easy to do. Because the numbers of detections are # different in each image. Therefore, this part needs to be done # per image. per_box_cls = per_box_cls[per_candidate_inds] per_box_cls, top_k_indices = \ per_box_cls.topk(per_pre_nms_top_n, sorted=False) per_candidate_nonzeros = \ per_candidate_inds.nonzero()[top_k_indices, :] per_box_loc = per_candidate_nonzeros[:, 0] per_class = per_candidate_nonzeros[:, 1] per_class += 1 detections = self.box_coder.decode( per_box_regression[per_box_loc, :].view(-1, 4), per_anchors.bbox[per_box_loc, :].view(-1, 4)) boxlist = BoxList(detections, per_anchors.size, mode="xyxy") boxlist.add_field("labels", per_class) boxlist.add_field("scores", per_box_cls) boxlist = boxlist.clip_to_image(remove_empty=False) boxlist = remove_small_boxes(boxlist, self.min_size) results.append(boxlist) return results