Source code for mmrotate.models.roi_heads.gv_ratio_roi_head
# Copyright (c) OpenMMLab. All rights reserved.
from mmdet.core import bbox2roi
from ..builder import ROTATED_HEADS
from .rotate_standard_roi_head import RotatedStandardRoIHead
[docs]@ROTATED_HEADS.register_module()
class GVRatioRoIHead(RotatedStandardRoIHead):
"""Gliding vertex roi head including one bbox head."""
[docs] def forward_dummy(self, x, proposals):
"""Dummy forward function.
Args:
x (list[Tensors]): list of multi-level img features.
proposals (list[Tensors]): list of region proposals.
Returns:
list[Tensors]: list of region of interest.
"""
# bbox head
outs = ()
rois = bbox2roi([proposals])
if self.with_bbox:
bbox_results = self._bbox_forward(x, rois)
outs = outs + (
bbox_results['cls_score'],
bbox_results['bbox_pred'],
bbox_results['fix_pred'],
bbox_results['ratio_pred'],
)
return outs
def _bbox_forward(self, x, rois):
"""Box head forward function used in both training and testing.
Args:
x (list[Tensor]): list of multi-level img features.
rois (list[Tensors]): list of region of interests.
Returns:
dict[str, Tensor]: a dictionary of bbox_results.
"""
bbox_feats = self.bbox_roi_extractor(
x[:self.bbox_roi_extractor.num_inputs], rois)
if self.with_shared_head:
bbox_feats = self.shared_head(bbox_feats)
cls_score, bbox_pred, fix_pred, ratio_pred = self.bbox_head(bbox_feats)
bbox_results = dict(
cls_score=cls_score,
bbox_pred=bbox_pred,
fix_pred=fix_pred,
ratio_pred=ratio_pred,
bbox_feats=bbox_feats)
return bbox_results
def _bbox_forward_train(self, x, sampling_results, gt_bboxes, gt_labels,
img_metas):
"""Run forward function and calculate loss for box head in training.
Args:
x (list[Tensor]): list of multi-level img features.
sampling_results (list[Tensor]): list of sampling results.
gt_bboxes (list[Tensor]): Ground truth bboxes for each image with
shape (num_gts, 5) in [cx, cy, w, h, a] format.
gt_labels (list[Tensor]): class indices corresponding to each box
img_metas (list[dict]): list of image info dict where each dict
has: 'img_shape', 'scale_factor', 'flip', and may also contain
'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
Returns:
dict[str, Tensor]: a dictionary of bbox_results.
"""
rois = bbox2roi([res.bboxes for res in sampling_results])
bbox_results = self._bbox_forward(x, rois)
bbox_targets = self.bbox_head.get_targets(sampling_results, gt_bboxes,
gt_labels, self.train_cfg)
loss_bbox = self.bbox_head.loss(bbox_results['cls_score'],
bbox_results['bbox_pred'],
bbox_results['fix_pred'],
bbox_results['ratio_pred'], rois,
*bbox_targets)
bbox_results.update(loss_bbox=loss_bbox)
return bbox_results
[docs] def simple_test_bboxes(self,
x,
img_metas,
proposals,
rcnn_test_cfg,
rescale=False):
"""Test only det bboxes without augmentation.
Args:
x (tuple[Tensor]): Feature maps of all scale level.
img_metas (list[dict]): Image meta info.
proposals (List[Tensor]): Region proposals.
rcnn_test_cfg (obj:`ConfigDict`): `test_cfg` of R-CNN.
rescale (bool): If True, return boxes in original image space.
Default: False.
Returns:
tuple[list[Tensor], list[Tensor]]: The first list contains \
the boxes of the corresponding image in a batch, each \
tensor has the shape (num_boxes, 5) and last dimension \
5 represent (cx, cy, w, h, a, score). Each Tensor \
in the second list is the labels with shape (num_boxes, ). \
The length of both lists should be equal to batch_size.
"""
rois = bbox2roi(proposals)
bbox_results = self._bbox_forward(x, rois)
img_shapes = tuple(meta['img_shape'] for meta in img_metas)
scale_factors = tuple(meta['scale_factor'] for meta in img_metas)
# split batch bbox prediction back to each image
cls_score = bbox_results['cls_score']
bbox_pred = bbox_results['bbox_pred']
fix_pred = bbox_results['fix_pred'],
ratio_pred = bbox_results['ratio_pred'],
num_proposals_per_img = tuple(len(p) for p in proposals)
rois = rois.split(num_proposals_per_img, 0)
cls_score = cls_score.split(num_proposals_per_img, 0)
# some detector with_reg is False, bbox_pred will be None
if bbox_pred is not None:
# the bbox prediction of some detectors like SABL is not Tensor
bbox_pred = bbox_pred.split(num_proposals_per_img, 0)
fix_pred = fix_pred[0].split(num_proposals_per_img, 0)
ratio_pred = ratio_pred[0].split(num_proposals_per_img, 0)
else:
bbox_pred = (None, ) * len(proposals)
fix_pred = (None, ) * len(proposals)
ratio_pred = (None, ) * len(proposals)
# apply bbox post-processing to each image individually
det_bboxes = []
det_labels = []
for i in range(len(proposals)):
det_bbox, det_label = self.bbox_head.get_bboxes(
rois[i],
cls_score[i],
bbox_pred[i],
fix_pred[i],
ratio_pred[i],
img_shapes[i],
scale_factors[i],
rescale=rescale,
cfg=self.test_cfg)
det_bboxes.append(det_bbox)
det_labels.append(det_label)
return det_bboxes, det_labels