def point_sample_fine_grained_features(features_list, feature_scales, boxes, point_coords):
cat_boxes = Boxes.cat(boxes)
num_boxes = [len(b) for b in boxes]
point_coords_wrt_image = get_point_coords_wrt_image(cat_boxes.tensor, point_coords)
split_point_coords_wrt_image = torch.split(point_coords_wrt_image, num_boxes)
point_features = []
for idx_img, point_coords_wrt_image_per_image in enumerate(split_point_coords_wrt_image):
point_features_per_image = []
for idx_feature, feature_map in enumerate(features_list):
h, w = feature_map.shape[-2:]
scale = torch.tensor([w, h], device=feature_map.device) / feature_scales[idx_feature]
point_coords_scaled = point_coords_wrt_image_per_image / scale
point_features_per_image.append(
point_sample(
feature_map[idx_img].unsqueeze(0),
point_coords_scaled.unsqueeze(0),
align_corners=False,
)
.squeeze(0)
.transpose(1, 0)
)
point_features.append(cat(point_features_per_image, dim=1))
return cat(point_features, dim=0), point_coords_wrt_image
def label_and_sample_anchors(self, anchors: List[Boxes],
gt_instances: List[Instances]):
anchors = Boxes.cat(anchors)
gt_boxes = [x.gt_boxes for x in gt_instances]
image_sizes = [x.image_size for x in gt_instances]
del gt_instances
gt_labels = []
matched_gt_boxes = []
for image_size_i, gt_boxes_i in zip(image_sizes, gt_boxes):
match_quality_matrix = retry_if_cuda_oom(pairwise_iou)(gt_boxes_i,
anchors)
matched_idxs, gt_labels_i = retry_if_cuda_oom(
self.anchor_matcher)(match_quality_matrix)
gt_labels_i = gt_labels_i.to(device=gt_boxes_i.device)
del match_quality_matrix
if self.anchor_boundary_thresh >= 0:
anchors_inside_image = anchors.inside_box(
image_size_i, self.anchor_boundary_thresh)
gt_labels_i[~anchors_inside_image] = -1
gt_labels_i = self._subsample_labels(gt_labels_i)
if len(gt_boxes_i) == 0:
matched_gt_boxes_i = torch.zeros_like(anchors.tensor)
else:
matched_gt_boxes_i = gt_boxes_i[matched_idxs].tensor
gt_labels.append(gt_labels_i)
matched_gt_boxes.append(matched_gt_boxes_i)
return gt_labels, matched_gt_boxes
def get_ground_truth(self, anchors, targets):
gt_classes = []
gt_anchors_deltas = []
anchors = Boxes.cat(anchors)
for targets_per_image in targets:
match_quality_matrix = pairwise_iou(targets_per_image.gt_boxes,
anchors)
gt_matched_idxs, anchor_labels = self.matcher(match_quality_matrix)
has_gt = len(targets_per_image) > 0
if has_gt:
matched_gt_boxes = targets_per_image.gt_boxes[gt_matched_idxs]
gt_anchors_reg_deltas_i = self.box2box_transform.get_deltas(
anchors.tensor, matched_gt_boxes.tensor)
gt_classes_i = targets_per_image.gt_classes[gt_matched_idxs]
gt_classes_i[anchor_labels == 0] = self.num_classes
gt_classes_i[anchor_labels == -1] = -1
else:
gt_classes_i = torch.zeros_like(
gt_matched_idxs) + self.num_classes
gt_anchors_reg_deltas_i = torch.zeros_like(anchors.tensor)
gt_classes.append(gt_classes_i)
gt_anchors_deltas.append(gt_anchors_reg_deltas_i)
return torch.stack(gt_classes), torch.stack(gt_anchors_deltas)
def label_anchors(self, anchors, gt_instances):
anchors = Boxes.cat(anchors)
gt_labels = []
matched_gt_boxes = []
for gt_per_image in gt_instances:
match_quality_matrix = pairwise_iou(gt_per_image.gt_boxes, anchors)
matched_idxs, anchor_labels = self.anchor_matcher(
match_quality_matrix)
del match_quality_matrix
if len(gt_per_image) > 0:
matched_gt_boxes_i = gt_per_image.gt_boxes.tensor[matched_idxs]
gt_labels_i = gt_per_image.gt_classes[matched_idxs]
gt_labels_i[anchor_labels == 0] = self.num_classes
gt_labels_i[anchor_labels == -1] = -1
else:
matched_gt_boxes_i = torch.zeros_like(anchors.tensor)
gt_labels_i = torch.zeros_like(matched_idxs) + self.num_classes
gt_labels.append(gt_labels_i)
matched_gt_boxes.append(matched_gt_boxes_i)
return gt_labels, matched_gt_boxes