Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,405 Bytes
b213d84 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
# Copyright (c) Facebook, Inc. and its affiliates.
from typing import List
import torch
from detectron2.config import CfgNode
from detectron2.structures import Instances
from detectron2.structures.boxes import matched_pairwise_iou
class DensePoseDataFilter:
def __init__(self, cfg: CfgNode):
self.iou_threshold = cfg.MODEL.ROI_DENSEPOSE_HEAD.FG_IOU_THRESHOLD
self.keep_masks = cfg.MODEL.ROI_DENSEPOSE_HEAD.COARSE_SEGM_TRAINED_BY_MASKS
@torch.no_grad()
def __call__(self, features: List[torch.Tensor], proposals_with_targets: List[Instances]):
"""
Filters proposals with targets to keep only the ones relevant for
DensePose training
Args:
features (list[Tensor]): input data as a list of features,
each feature is a tensor. Axis 0 represents the number of
images `N` in the input data; axes 1-3 are channels,
height, and width, which may vary between features
(e.g., if a feature pyramid is used).
proposals_with_targets (list[Instances]): length `N` list of
`Instances`. The i-th `Instances` contains instances
(proposals, GT) for the i-th input image,
Returns:
list[Tensor]: filtered features
list[Instances]: filtered proposals
"""
proposals_filtered = []
# TODO: the commented out code was supposed to correctly deal with situations
# where no valid DensePose GT is available for certain images. The corresponding
# image features were sliced and proposals were filtered. This led to performance
# deterioration, both in terms of runtime and in terms of evaluation results.
#
# feature_mask = torch.ones(
# len(proposals_with_targets),
# dtype=torch.bool,
# device=features[0].device if len(features) > 0 else torch.device("cpu"),
# )
for i, proposals_per_image in enumerate(proposals_with_targets):
if not proposals_per_image.has("gt_densepose") and (
not proposals_per_image.has("gt_masks") or not self.keep_masks
):
# feature_mask[i] = 0
continue
gt_boxes = proposals_per_image.gt_boxes
est_boxes = proposals_per_image.proposal_boxes
# apply match threshold for densepose head
iou = matched_pairwise_iou(gt_boxes, est_boxes)
iou_select = iou > self.iou_threshold
proposals_per_image = proposals_per_image[iou_select] # pyre-ignore[6]
N_gt_boxes = len(proposals_per_image.gt_boxes)
assert N_gt_boxes == len(proposals_per_image.proposal_boxes), (
f"The number of GT boxes {N_gt_boxes} is different from the "
f"number of proposal boxes {len(proposals_per_image.proposal_boxes)}"
)
# filter out any target without suitable annotation
if self.keep_masks:
gt_masks = (
proposals_per_image.gt_masks
if hasattr(proposals_per_image, "gt_masks")
else [None] * N_gt_boxes
)
else:
gt_masks = [None] * N_gt_boxes
gt_densepose = (
proposals_per_image.gt_densepose
if hasattr(proposals_per_image, "gt_densepose")
else [None] * N_gt_boxes
)
assert len(gt_masks) == N_gt_boxes
assert len(gt_densepose) == N_gt_boxes
selected_indices = [
i
for i, (dp_target, mask_target) in enumerate(zip(gt_densepose, gt_masks))
if (dp_target is not None) or (mask_target is not None)
]
# if not len(selected_indices):
# feature_mask[i] = 0
# continue
if len(selected_indices) != N_gt_boxes:
proposals_per_image = proposals_per_image[selected_indices] # pyre-ignore[6]
assert len(proposals_per_image.gt_boxes) == len(proposals_per_image.proposal_boxes)
proposals_filtered.append(proposals_per_image)
# features_filtered = [feature[feature_mask] for feature in features]
# return features_filtered, proposals_filtered
return features, proposals_filtered
|