import torch
import torch.nn as nn
from mmcv.cnn import normal_init
from mmdet.core import (anchor_inside_flags, build_anchor_generator,
build_assigner, build_bbox_coder, build_sampler,
force_fp32, images_to_levels, multi_apply,
multiclass_nms, unmap)
from ..builder import HEADS, build_loss
from .base_dense_head import BaseDenseHead
[docs]@HEADS.register_module()
class AnchorHead(BaseDenseHead):
"""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 on decoded bounding boxes. Default: False
background_label (int | None): Label ID of background, set as 0 for
RPN and num_classes for other heads. It will automatically set as
num_classes if None is given.
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.
""" # 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',
target_means=(.0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0)),
reg_decoded_bbox=False,
background_label=None,
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):
super(AnchorHead, self).__init__()
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)
# TODO better way to determine whether sample or not
self.sampling = loss_cls['type'] not in [
'FocalLoss', 'GHMC', 'QualityFocalLoss'
]
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.background_label = (
num_classes if background_label is None else background_label)
# background_label should be either 0 or num_classes
assert (self.background_label == 0
or self.background_label == num_classes)
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)
# use PseudoSampler when sampling is False
if self.sampling and hasattr(self.train_cfg, 'sampler'):
sampler_cfg = self.train_cfg.sampler
else:
sampler_cfg = dict(type='PseudoSampler')
self.sampler = build_sampler(sampler_cfg, context=self)
self.fp16_enabled = False
self.anchor_generator = build_anchor_generator(anchor_generator)
# usually the numbers of anchors for each level are the same
# except SSD detectors
self.num_anchors = self.anchor_generator.num_base_anchors[0]
self._init_layers()
def _init_layers(self):
"""Initialize layers of the head."""
self.conv_cls = nn.Conv2d(self.in_channels,
self.num_anchors * self.cls_out_channels, 1)
self.conv_reg = nn.Conv2d(self.in_channels, self.num_anchors * 4, 1)
[docs] def init_weights(self):
"""Initialize weights of the head."""
normal_init(self.conv_cls, std=0.01)
normal_init(self.conv_reg, std=0.01)
[docs] 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_anchors * num_classes.
bbox_pred (Tensor): Box energies / deltas for a single scale
level, the channels number is num_anchors * 4.
"""
cls_score = self.conv_cls(x)
bbox_pred = self.conv_reg(x)
return cls_score, bbox_pred
[docs] 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: Usually 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_anchors * num_classes.
bbox_preds (list[Tensor]): Box energies / deltas for all scale
levels, each is a 4D-tensor, the channels number is
num_anchors * 4.
"""
return multi_apply(self.forward_single, feats)
[docs] 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.anchor_generator.grid_anchors(
featmap_sizes, 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.anchor_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).
img_meta (dict): Meta info of the image.
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, ) * 6
# 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.background_label,
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, this time FG is 1
labels[pos_inds] = 1
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.background_label) # 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)
[docs] 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:
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)
[docs] 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 wight
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:
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
[docs] @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.anchor_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)
[docs] @force_fp32(apply_to=('cls_scores', 'bbox_preds'))
def get_bboxes(self,
cls_scores,
bbox_preds,
img_metas,
cfg=None,
rescale=False):
"""Transform network output for a batch into bbox predictions.
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)
img_metas (list[dict]): Meta information of each image, e.g.,
image size, scaling factor, etc.
cfg (mmcv.Config | None): Test / postprocessing configuration,
if None, test_cfg would be used
rescale (bool): If True, return boxes in original image space.
Default: False.
Returns:
list[tuple[Tensor, Tensor]]: Each item in result_list is 2-tuple.
The first item is an (n, 5) tensor, where the first 4 columns
are bounding box positions (tl_x, tl_y, br_x, br_y) and the
5-th column is a score between 0 and 1. The second item is a
(n,) tensor where each item is the predicted class labelof the
corresponding box.
Example:
>>> import mmcv
>>> self = AnchorHead(
>>> num_classes=9,
>>> in_channels=1,
>>> anchor_generator=dict(
>>> type='AnchorGenerator',
>>> scales=[8],
>>> ratios=[0.5, 1.0, 2.0],
>>> strides=[4,]))
>>> img_metas = [{'img_shape': (32, 32, 3), 'scale_factor': 1}]
>>> cfg = mmcv.Config(dict(
>>> score_thr=0.00,
>>> nms=dict(type='nms', iou_thr=1.0),
>>> max_per_img=10))
>>> feat = torch.rand(1, 1, 3, 3)
>>> cls_score, bbox_pred = self.forward_single(feat)
>>> # note the input lists are over different levels, not images
>>> cls_scores, bbox_preds = [cls_score], [bbox_pred]
>>> result_list = self.get_bboxes(cls_scores, bbox_preds,
>>> img_metas, cfg)
>>> det_bboxes, det_labels = result_list[0]
>>> assert len(result_list) == 1
>>> assert det_bboxes.shape[1] == 5
>>> assert len(det_bboxes) == len(det_labels) == cfg.max_per_img
"""
assert len(cls_scores) == len(bbox_preds)
num_levels = len(cls_scores)
device = cls_scores[0].device
featmap_sizes = [cls_scores[i].shape[-2:] for i in range(num_levels)]
mlvl_anchors = self.anchor_generator.grid_anchors(
featmap_sizes, device=device)
result_list = []
for img_id in range(len(img_metas)):
cls_score_list = [
cls_scores[i][img_id].detach() for i in range(num_levels)
]
bbox_pred_list = [
bbox_preds[i][img_id].detach() for i in range(num_levels)
]
img_shape = img_metas[img_id]['img_shape']
scale_factor = img_metas[img_id]['scale_factor']
proposals = self._get_bboxes_single(cls_score_list, bbox_pred_list,
mlvl_anchors, img_shape,
scale_factor, cfg, rescale)
result_list.append(proposals)
return result_list
def _get_bboxes_single(self,
cls_score_list,
bbox_pred_list,
mlvl_anchors,
img_shape,
scale_factor,
cfg,
rescale=False):
"""Transform outputs for a single batch item into bbox predictions.
Args:
cls_score_list (list[Tensor]): Box scores for a single scale level
Has shape (num_anchors * num_classes, H, W).
bbox_pred_list (list[Tensor]): Box energies / deltas for a single
scale level with shape (num_anchors * 4, H, W).
mlvl_anchors (list[Tensor]): Box reference for a single scale level
with shape (num_total_anchors, 4).
img_shape (tuple[int]): Shape of the input image,
(height, width, 3).
scale_factor (ndarray): Scale factor of the image arange as
(w_scale, h_scale, w_scale, h_scale).
cfg (mmcv.Config): Test / postprocessing configuration,
if None, test_cfg would be used.
rescale (bool): If True, return boxes in original image space.
Returns:
Tensor: Labeled boxes in shape (n, 5), where the first 4 columns
are bounding box positions (tl_x, tl_y, br_x, br_y) and the
5-th column is a score between 0 and 1.
"""
cfg = self.test_cfg if cfg is None else cfg
assert len(cls_score_list) == len(bbox_pred_list) == len(mlvl_anchors)
mlvl_bboxes = []
mlvl_scores = []
for cls_score, bbox_pred, anchors in zip(cls_score_list,
bbox_pred_list, mlvl_anchors):
assert cls_score.size()[-2:] == bbox_pred.size()[-2:]
cls_score = cls_score.permute(1, 2,
0).reshape(-1, self.cls_out_channels)
if self.use_sigmoid_cls:
scores = cls_score.sigmoid()
else:
scores = cls_score.softmax(-1)
bbox_pred = bbox_pred.permute(1, 2, 0).reshape(-1, 4)
nms_pre = cfg.get('nms_pre', -1)
if nms_pre > 0 and scores.shape[0] > nms_pre:
# Get maximum scores for foreground classes.
if self.use_sigmoid_cls:
max_scores, _ = scores.max(dim=1)
else:
# remind that we set FG labels to [0, num_class-1]
# since mmdet v2.0
# BG cat_id: num_class
max_scores, _ = scores[:, :-1].max(dim=1)
_, topk_inds = max_scores.topk(nms_pre)
anchors = anchors[topk_inds, :]
bbox_pred = bbox_pred[topk_inds, :]
scores = scores[topk_inds, :]
bboxes = self.bbox_coder.decode(
anchors, bbox_pred, max_shape=img_shape)
mlvl_bboxes.append(bboxes)
mlvl_scores.append(scores)
mlvl_bboxes = torch.cat(mlvl_bboxes)
if rescale:
mlvl_bboxes /= mlvl_bboxes.new_tensor(scale_factor)
mlvl_scores = torch.cat(mlvl_scores)
if self.use_sigmoid_cls:
# Add a dummy background class to the backend when using sigmoid
# remind that we set FG labels to [0, num_class-1] since mmdet v2.0
# BG cat_id: num_class
padding = mlvl_scores.new_zeros(mlvl_scores.shape[0], 1)
mlvl_scores = torch.cat([mlvl_scores, padding], dim=1)
det_bboxes, det_labels = multiclass_nms(mlvl_bboxes, mlvl_scores,
cfg.score_thr, cfg.nms,
cfg.max_per_img)
return det_bboxes, det_labels