|
- # Copyright (c) OpenMMLab. All rights reserved.
- import torch
-
- from mmdet.core import bbox2result
- from ..builder import DETECTORS, build_head
- from .single_stage import SingleStageDetector
-
-
- @DETECTORS.register_module()
- class YOLACT(SingleStageDetector):
- """Implementation of `YOLACT <https://arxiv.org/abs/1904.02689>`_"""
-
- def __init__(self,
- backbone,
- neck,
- bbox_head,
- segm_head,
- mask_head,
- train_cfg=None,
- test_cfg=None,
- pretrained=None,
- init_cfg=None):
- super(YOLACT, self).__init__(backbone, neck, bbox_head, train_cfg,
- test_cfg, pretrained, init_cfg)
- self.segm_head = build_head(segm_head)
- self.mask_head = build_head(mask_head)
-
- def forward_dummy(self, img):
- """Used for computing network flops.
-
- See `mmdetection/tools/analysis_tools/get_flops.py`
- """
- feat = self.extract_feat(img)
- bbox_outs = self.bbox_head(feat)
- prototypes = self.mask_head.forward_dummy(feat[0])
- return (bbox_outs, prototypes)
-
- def forward_train(self,
- img,
- img_metas,
- gt_bboxes,
- gt_labels,
- gt_bboxes_ignore=None,
- gt_masks=None):
- """
- Args:
- img (Tensor): of shape (N, C, H, W) encoding input images.
- Typically these should be mean centered and std scaled.
- 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'.
- For details on the values of these keys see
- `mmdet/datasets/pipelines/formatting.py:Collect`.
- 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
- gt_bboxes_ignore (None | list[Tensor]): specify which bounding
- boxes can be ignored when computing the loss.
- gt_masks (None | Tensor) : true segmentation masks for each box
- used if the architecture supports a segmentation task.
-
- Returns:
- dict[str, Tensor]: a dictionary of loss components
- """
- # convert Bitmap mask or Polygon Mask to Tensor here
- gt_masks = [
- gt_mask.to_tensor(dtype=torch.uint8, device=img.device)
- for gt_mask in gt_masks
- ]
-
- x = self.extract_feat(img)
-
- cls_score, bbox_pred, coeff_pred = self.bbox_head(x)
- bbox_head_loss_inputs = (cls_score, bbox_pred) + (gt_bboxes, gt_labels,
- img_metas)
- losses, sampling_results = self.bbox_head.loss(
- *bbox_head_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
-
- segm_head_outs = self.segm_head(x[0])
- loss_segm = self.segm_head.loss(segm_head_outs, gt_masks, gt_labels)
- losses.update(loss_segm)
-
- mask_pred = self.mask_head(x[0], coeff_pred, gt_bboxes, img_metas,
- sampling_results)
- loss_mask = self.mask_head.loss(mask_pred, gt_masks, gt_bboxes,
- img_metas, sampling_results)
- losses.update(loss_mask)
-
- # check NaN and Inf
- for loss_name in losses.keys():
- assert torch.isfinite(torch.stack(losses[loss_name]))\
- .all().item(), '{} becomes infinite or NaN!'\
- .format(loss_name)
-
- return losses
-
- def simple_test(self, img, img_metas, rescale=False):
- """Test function without test-time augmentation."""
- feat = self.extract_feat(img)
- det_bboxes, det_labels, det_coeffs = self.bbox_head.simple_test(
- feat, img_metas, rescale=rescale)
- bbox_results = [
- bbox2result(det_bbox, det_label, self.bbox_head.num_classes)
- for det_bbox, det_label in zip(det_bboxes, det_labels)
- ]
-
- segm_results = self.mask_head.simple_test(
- feat,
- det_bboxes,
- det_labels,
- det_coeffs,
- img_metas,
- rescale=rescale)
-
- return list(zip(bbox_results, segm_results))
-
- def aug_test(self, imgs, img_metas, rescale=False):
- """Test with augmentations."""
- raise NotImplementedError(
- 'YOLACT does not support test-time augmentation')
|