# Copyright (c) OpenMMLab. All rights reserved. import warnings import torch import torch.nn as nn from mmcv.runner import force_fp32 from mmdet.core import (anchor_inside_flags, build_assigner, build_bbox_coder, build_prior_generator, build_sampler, images_to_levels, multi_apply, unmap) from ..builder import HEADS, build_loss from .base_dense_head import BaseDenseHead from .dense_test_mixins import BBoxTestMixin @HEADS.register_module() class AnchorHead(BaseDenseHead, BBoxTestMixin): """Anchor-based head (RPN, RetinaNet, SSD, etc.). Args: num_classes (int): Number of categories excluding the background category. in_channels (int): Number of channels in the input feature map. feat_channels (int): Number of hidden channels. Used in child classes. anchor_generator (dict): Config dict for anchor generator bbox_coder (dict): Config of bounding box coder. reg_decoded_bbox (bool): If true, the regression loss would be applied directly on decoded bounding boxes, converting both the predicted boxes and regression targets to absolute coordinates format. Default False. It should be `True` when using `IoULoss`, `GIoULoss`, or `DIoULoss` in the bbox head. loss_cls (dict): Config of classification loss. loss_bbox (dict): Config of localization loss. train_cfg (dict): Training config of anchor head. test_cfg (dict): Testing config of anchor head. init_cfg (dict or list[dict], optional): Initialization config dict. """ # noqa: W605 def __init__(self, num_classes, in_channels, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8, 16, 32], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', clip_border=True, target_means=(.0, .0, .0, .0), target_stds=(1.0, 1.0, 1.0, 1.0)), reg_decoded_bbox=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict( type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0), train_cfg=None, test_cfg=None, init_cfg=dict(type='Normal', layer='Conv2d', std=0.01)): super(AnchorHead, self).__init__(init_cfg) self.in_channels = in_channels self.num_classes = num_classes self.feat_channels = feat_channels self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False) if self.use_sigmoid_cls: self.cls_out_channels = num_classes else: self.cls_out_channels = num_classes + 1 if self.cls_out_channels <= 0: raise ValueError(f'num_classes={num_classes} is too small') self.reg_decoded_bbox = reg_decoded_bbox self.bbox_coder = build_bbox_coder(bbox_coder) self.loss_cls = build_loss(loss_cls) self.loss_bbox = build_loss(loss_bbox) self.train_cfg = train_cfg self.test_cfg = test_cfg if self.train_cfg: self.assigner = build_assigner(self.train_cfg.assigner) if hasattr(self.train_cfg, 'sampler') and self.train_cfg.sampler.type.split( '.')[-1] != 'PseudoSampler': self.sampling = True sampler_cfg = self.train_cfg.sampler # avoid BC-breaking if loss_cls['type'] in [ 'FocalLoss', 'GHMC', 'QualityFocalLoss' ]: warnings.warn( 'DeprecationWarning: Determining whether to sampling' 'by loss type is deprecated, please delete sampler in' 'your config when using `FocalLoss`, `GHMC`, ' '`QualityFocalLoss` or other FocalLoss variant.') self.sampling = False sampler_cfg = dict(type='PseudoSampler') else: self.sampling = False sampler_cfg = dict(type='PseudoSampler') self.sampler = build_sampler(sampler_cfg, context=self) self.fp16_enabled = False self.prior_generator = build_prior_generator(anchor_generator) # Usually the numbers of anchors for each level are the same # except SSD detectors. So it is an int in the most dense # heads but a list of int in SSDHead self.num_base_priors = self.prior_generator.num_base_priors[0] self._init_layers() @property def num_anchors(self): warnings.warn('DeprecationWarning: `num_anchors` is deprecated, ' 'for consistency or also use ' '`num_base_priors` instead') return self.prior_generator.num_base_priors[0] @property def anchor_generator(self): warnings.warn('DeprecationWarning: anchor_generator is deprecated, ' 'please use "prior_generator" instead') return self.prior_generator def _init_layers(self): """Initialize layers of the head.""" self.conv_cls = nn.Conv2d(self.in_channels, self.num_base_priors * self.cls_out_channels, 1) self.conv_reg = nn.Conv2d(self.in_channels, self.num_base_priors * 4, 1) def forward_single(self, x): """Forward feature of a single scale level. Args: x (Tensor): Features of a single scale level. Returns: tuple: cls_score (Tensor): Cls scores for a single scale level \ the channels number is num_base_priors * num_classes. bbox_pred (Tensor): Box energies / deltas for a single scale \ level, the channels number is num_base_priors * 4. """ cls_score = self.conv_cls(x) bbox_pred = self.conv_reg(x) return cls_score, bbox_pred def forward(self, feats): """Forward features from the upstream network. Args: feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor. Returns: tuple: A tuple of classification scores and bbox prediction. - cls_scores (list[Tensor]): Classification scores for all \ scale levels, each is a 4D-tensor, the channels number \ is num_base_priors * num_classes. - bbox_preds (list[Tensor]): Box energies / deltas for all \ scale levels, each is a 4D-tensor, the channels number \ is num_base_priors * 4. """ return multi_apply(self.forward_single, feats) def get_anchors(self, featmap_sizes, img_metas, device='cuda'): """Get anchors according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_metas (list[dict]): Image meta info. device (torch.device | str): Device for returned tensors Returns: tuple: anchor_list (list[Tensor]): Anchors of each image. valid_flag_list (list[Tensor]): Valid flags of each image. """ num_imgs = len(img_metas) # since feature map sizes of all images are the same, we only compute # anchors for one time multi_level_anchors = self.prior_generator.grid_priors( featmap_sizes, device=device) anchor_list = [multi_level_anchors for _ in range(num_imgs)] # for each image, we compute valid flags of multi level anchors valid_flag_list = [] for img_id, img_meta in enumerate(img_metas): multi_level_flags = self.prior_generator.valid_flags( featmap_sizes, img_meta['pad_shape'], device) valid_flag_list.append(multi_level_flags) return anchor_list, valid_flag_list def _get_targets_single(self, flat_anchors, valid_flags, gt_bboxes, gt_bboxes_ignore, gt_labels, img_meta, label_channels=1, unmap_outputs=True): """Compute regression and classification targets for anchors in a single image. Args: flat_anchors (Tensor): Multi-level anchors of the image, which are concatenated into a single tensor of shape (num_anchors ,4) valid_flags (Tensor): Multi level valid flags of the image, which are concatenated into a single tensor of shape (num_anchors,). gt_bboxes (Tensor): Ground truth bboxes of the image, shape (num_gts, 4). gt_bboxes_ignore (Tensor): Ground truth bboxes to be ignored, shape (num_ignored_gts, 4). img_meta (dict): Meta info of the image. gt_labels (Tensor): Ground truth labels of each box, shape (num_gts,). label_channels (int): Channel of label. unmap_outputs (bool): Whether to map outputs back to the original set of anchors. Returns: tuple: labels_list (list[Tensor]): Labels of each level label_weights_list (list[Tensor]): Label weights of each level bbox_targets_list (list[Tensor]): BBox targets of each level bbox_weights_list (list[Tensor]): BBox weights of each level num_total_pos (int): Number of positive samples in all images num_total_neg (int): Number of negative samples in all images """ inside_flags = anchor_inside_flags(flat_anchors, valid_flags, img_meta['img_shape'][:2], self.train_cfg.allowed_border) if not inside_flags.any(): return (None, ) * 7 # assign gt and sample anchors anchors = flat_anchors[inside_flags, :] assign_result = self.assigner.assign( anchors, gt_bboxes, gt_bboxes_ignore, None if self.sampling else gt_labels) sampling_result = self.sampler.sample(assign_result, anchors, gt_bboxes) num_valid_anchors = anchors.shape[0] bbox_targets = torch.zeros_like(anchors) bbox_weights = torch.zeros_like(anchors) labels = anchors.new_full((num_valid_anchors, ), self.num_classes, dtype=torch.long) label_weights = anchors.new_zeros(num_valid_anchors, dtype=torch.float) pos_inds = sampling_result.pos_inds neg_inds = sampling_result.neg_inds if len(pos_inds) > 0: if not self.reg_decoded_bbox: pos_bbox_targets = self.bbox_coder.encode( sampling_result.pos_bboxes, sampling_result.pos_gt_bboxes) else: pos_bbox_targets = sampling_result.pos_gt_bboxes bbox_targets[pos_inds, :] = pos_bbox_targets bbox_weights[pos_inds, :] = 1.0 if gt_labels is None: # Only rpn gives gt_labels as None # Foreground is the first class since v2.5.0 labels[pos_inds] = 0 else: labels[pos_inds] = gt_labels[ sampling_result.pos_assigned_gt_inds] if self.train_cfg.pos_weight <= 0: label_weights[pos_inds] = 1.0 else: label_weights[pos_inds] = self.train_cfg.pos_weight if len(neg_inds) > 0: label_weights[neg_inds] = 1.0 # map up to original set of anchors if unmap_outputs: num_total_anchors = flat_anchors.size(0) labels = unmap( labels, num_total_anchors, inside_flags, fill=self.num_classes) # fill bg label label_weights = unmap(label_weights, num_total_anchors, inside_flags) bbox_targets = unmap(bbox_targets, num_total_anchors, inside_flags) bbox_weights = unmap(bbox_weights, num_total_anchors, inside_flags) return (labels, label_weights, bbox_targets, bbox_weights, pos_inds, neg_inds, sampling_result) def get_targets(self, anchor_list, valid_flag_list, gt_bboxes_list, img_metas, gt_bboxes_ignore_list=None, gt_labels_list=None, label_channels=1, unmap_outputs=True, return_sampling_results=False): """Compute regression and classification targets for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Multi level anchors of each image. The outer list indicates images, and the inner list corresponds to feature levels of the image. Each element of the inner list is a tensor of shape (num_anchors, 4). valid_flag_list (list[list[Tensor]]): Multi level valid flags of each image. The outer list indicates images, and the inner list corresponds to feature levels of the image. Each element of the inner list is a tensor of shape (num_anchors, ) gt_bboxes_list (list[Tensor]): Ground truth bboxes of each image. img_metas (list[dict]): Meta info of each image. gt_bboxes_ignore_list (list[Tensor]): Ground truth bboxes to be ignored. gt_labels_list (list[Tensor]): Ground truth labels of each box. label_channels (int): Channel of label. unmap_outputs (bool): Whether to map outputs back to the original set of anchors. Returns: tuple: Usually returns a tuple containing learning targets. - labels_list (list[Tensor]): Labels of each level. - label_weights_list (list[Tensor]): Label weights of each level. - bbox_targets_list (list[Tensor]): BBox targets of each level. - bbox_weights_list (list[Tensor]): BBox weights of each level. - num_total_pos (int): Number of positive samples in all images. - num_total_neg (int): Number of negative samples in all images. additional_returns: This function enables user-defined returns from `self._get_targets_single`. These returns are currently refined to properties at each feature map (i.e. having HxW dimension). The results will be concatenated after the end """ num_imgs = len(img_metas) assert len(anchor_list) == len(valid_flag_list) == num_imgs # anchor number of multi levels num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]] # concat all level anchors to a single tensor concat_anchor_list = [] concat_valid_flag_list = [] for i in range(num_imgs): assert len(anchor_list[i]) == len(valid_flag_list[i]) concat_anchor_list.append(torch.cat(anchor_list[i])) concat_valid_flag_list.append(torch.cat(valid_flag_list[i])) # compute targets for each image if gt_bboxes_ignore_list is None: gt_bboxes_ignore_list = [None for _ in range(num_imgs)] if gt_labels_list is None: gt_labels_list = [None for _ in range(num_imgs)] results = multi_apply( self._get_targets_single, concat_anchor_list, concat_valid_flag_list, gt_bboxes_list, gt_bboxes_ignore_list, gt_labels_list, img_metas, label_channels=label_channels, unmap_outputs=unmap_outputs) (all_labels, all_label_weights, all_bbox_targets, all_bbox_weights, pos_inds_list, neg_inds_list, sampling_results_list) = results[:7] rest_results = list(results[7:]) # user-added return values # no valid anchors if any([labels is None for labels in all_labels]): return None # sampled anchors of all images num_total_pos = sum([max(inds.numel(), 1) for inds in pos_inds_list]) num_total_neg = sum([max(inds.numel(), 1) for inds in neg_inds_list]) # split targets to a list w.r.t. multiple levels labels_list = images_to_levels(all_labels, num_level_anchors) label_weights_list = images_to_levels(all_label_weights, num_level_anchors) bbox_targets_list = images_to_levels(all_bbox_targets, num_level_anchors) bbox_weights_list = images_to_levels(all_bbox_weights, num_level_anchors) res = (labels_list, label_weights_list, bbox_targets_list, bbox_weights_list, num_total_pos, num_total_neg) if return_sampling_results: res = res + (sampling_results_list, ) for i, r in enumerate(rest_results): # user-added return values rest_results[i] = images_to_levels(r, num_level_anchors) return res + tuple(rest_results) def loss_single(self, cls_score, bbox_pred, anchors, labels, label_weights, bbox_targets, bbox_weights, num_total_samples): """Compute loss of a single scale level. Args: cls_score (Tensor): Box scores for each scale level Has shape (N, num_anchors * num_classes, H, W). bbox_pred (Tensor): Box energies / deltas for each scale level with shape (N, num_anchors * 4, H, W). anchors (Tensor): Box reference for each scale level with shape (N, num_total_anchors, 4). labels (Tensor): Labels of each anchors with shape (N, num_total_anchors). label_weights (Tensor): Label weights of each anchor with shape (N, num_total_anchors) bbox_targets (Tensor): BBox regression targets of each anchor weight shape (N, num_total_anchors, 4). bbox_weights (Tensor): BBox regression loss weights of each anchor with shape (N, num_total_anchors, 4). num_total_samples (int): If sampling, num total samples equal to the number of total anchors; Otherwise, it is the number of positive anchors. Returns: dict[str, Tensor]: A dictionary of loss components. """ # classification loss labels = labels.reshape(-1) label_weights = label_weights.reshape(-1) cls_score = cls_score.permute(0, 2, 3, 1).reshape(-1, self.cls_out_channels) loss_cls = self.loss_cls( cls_score, labels, label_weights, avg_factor=num_total_samples) # regression loss bbox_targets = bbox_targets.reshape(-1, 4) bbox_weights = bbox_weights.reshape(-1, 4) bbox_pred = bbox_pred.permute(0, 2, 3, 1).reshape(-1, 4) if self.reg_decoded_bbox: # When the regression loss (e.g. `IouLoss`, `GIouLoss`) # is applied directly on the decoded bounding boxes, it # decodes the already encoded coordinates to absolute format. anchors = anchors.reshape(-1, 4) bbox_pred = self.bbox_coder.decode(anchors, bbox_pred) loss_bbox = self.loss_bbox( bbox_pred, bbox_targets, bbox_weights, avg_factor=num_total_samples) return loss_cls, loss_bbox @force_fp32(apply_to=('cls_scores', 'bbox_preds')) def loss(self, cls_scores, bbox_preds, gt_bboxes, gt_labels, img_metas, gt_bboxes_ignore=None): """Compute losses of the head. Args: cls_scores (list[Tensor]): Box scores for each scale level Has shape (N, num_anchors * num_classes, H, W) bbox_preds (list[Tensor]): Box energies / deltas for each scale level with shape (N, num_anchors * 4, H, W) gt_bboxes (list[Tensor]): Ground truth bboxes for each image with shape (num_gts, 4) in [tl_x, tl_y, br_x, br_y] format. gt_labels (list[Tensor]): class indices corresponding to each box img_metas (list[dict]): Meta information of each image, e.g., image size, scaling factor, etc. gt_bboxes_ignore (None | list[Tensor]): specify which bounding boxes can be ignored when computing the loss. Default: None Returns: dict[str, Tensor]: A dictionary of loss components. """ featmap_sizes = [featmap.size()[-2:] for featmap in cls_scores] assert len(featmap_sizes) == self.prior_generator.num_levels device = cls_scores[0].device anchor_list, valid_flag_list = self.get_anchors( featmap_sizes, img_metas, device=device) label_channels = self.cls_out_channels if self.use_sigmoid_cls else 1 cls_reg_targets = self.get_targets( anchor_list, valid_flag_list, gt_bboxes, img_metas, gt_bboxes_ignore_list=gt_bboxes_ignore, gt_labels_list=gt_labels, label_channels=label_channels) if cls_reg_targets is None: return None (labels_list, label_weights_list, bbox_targets_list, bbox_weights_list, num_total_pos, num_total_neg) = cls_reg_targets num_total_samples = ( num_total_pos + num_total_neg if self.sampling else num_total_pos) # anchor number of multi levels num_level_anchors = [anchors.size(0) for anchors in anchor_list[0]] # concat all level anchors and flags to a single tensor concat_anchor_list = [] for i in range(len(anchor_list)): concat_anchor_list.append(torch.cat(anchor_list[i])) all_anchor_list = images_to_levels(concat_anchor_list, num_level_anchors) losses_cls, losses_bbox = multi_apply( self.loss_single, cls_scores, bbox_preds, all_anchor_list, labels_list, label_weights_list, bbox_targets_list, bbox_weights_list, num_total_samples=num_total_samples) return dict(loss_cls=losses_cls, loss_bbox=losses_bbox) def aug_test(self, feats, img_metas, rescale=False): """Test function with test time augmentation. Args: feats (list[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape NxCxHxW, which contains features for all images in the batch. img_metas (list[list[dict]]): the outer list indicates test-time augs (multiscale, flip, etc.) and the inner list indicates images in a batch. each dict has image information. rescale (bool, optional): Whether to rescale the results. Defaults to False. Returns: list[tuple[Tensor, Tensor]]: Each item in result_list is 2-tuple. The first item is ``bboxes`` with shape (n, 5), where 5 represent (tl_x, tl_y, br_x, br_y, score). The shape of the second tensor in the tuple is ``labels`` with shape (n,), The length of list should always be 1. """ return self.aug_test_bboxes(feats, img_metas, rescale=rescale)