def __call__(self, proposals, mask_logits, targets):
"""
Arguments:
proposals (list[BoxList])
mask_logits (Tensor)
targets (list[BoxList])
Return:
mask_loss (Tensor): scalar tensor containing the loss
"""
labels, mask_targets = self.prepare_targets(proposals, targets)
labels = cat(labels, dim=0)
mask_targets = cat(mask_targets, dim=0)
positive_inds = torch.nonzero(labels > 0).squeeze(1)
labels_pos = labels[positive_inds]
# torch.mean (in binary_cross_entropy_with_logits) doesn't
# accept empty tensors, so handle it separately
if mask_targets.numel() == 0:
return mask_logits.sum() * 0
mask_loss = F.binary_cross_entropy_with_logits(
mask_logits[positive_inds, labels_pos], mask_targets
)
return mask_loss
def __call__(self, proposals, keypoint_logits):
heatmaps = []
valid = []
for proposals_per_image in proposals:
kp = proposals_per_image.get_field("keypoints")
heatmaps_per_image, valid_per_image = project_keypoints_to_heatmap(
kp, proposals_per_image, self.discretization_size)
heatmaps.append(heatmaps_per_image.view(-1))
valid.append(valid_per_image.view(-1))
keypoint_targets = cat(heatmaps, dim=0)
valid = cat(valid, dim=0).to(dtype=torch.bool)
valid = torch.nonzero(valid).squeeze(1)
# torch.mean (in binary_cross_entropy_with_logits) does'nt
# accept empty tensors, so handle it sepaartely
if keypoint_targets.numel() == 0 or len(valid) == 0:
return keypoint_logits.sum() * 0
N, K, H, W = keypoint_logits.shape
keypoint_logits = keypoint_logits.view(N * K, H * W)
keypoint_loss = F.cross_entropy(keypoint_logits[valid],
keypoint_targets[valid])
return keypoint_loss
def __call__(self, class_logits, box_regression):
"""
Computes the loss for Faster R-CNN.
This requires that the subsample method has been called beforehand.
Arguments:
class_logits (list[Tensor])
box_regression (list[Tensor])
Returns:
classification_loss (Tensor)
box_loss (Tensor)
"""
class_logits = cat(class_logits, dim=0)
box_regression = cat(box_regression, dim=0)
device = class_logits.device
if not hasattr(self, "_proposals"):
raise RuntimeError("subsample needs to be called before")
proposals = self._proposals
labels = cat([proposal.get_field("labels") for proposal in proposals],
dim=0)
regression_targets = cat([
proposal.get_field("regression_targets") for proposal in proposals
],
dim=0)
classification_loss = F.cross_entropy(class_logits, labels)
# get indices that correspond to the regression targets for
# the corresponding ground truth labels, to be used with
# advanced indexing
sampled_pos_inds_subset = torch.nonzero(labels > 0).squeeze(1)
labels_pos = labels[sampled_pos_inds_subset]
if self.cls_agnostic_bbox_reg:
map_inds = torch.tensor([4, 5, 6, 7], device=device)
else:
map_inds = 4 * labels_pos[:, None] + torch.tensor([0, 1, 2, 3],
device=device)
box_loss = smooth_l1_loss(
box_regression[sampled_pos_inds_subset[:, None], map_inds],
regression_targets[sampled_pos_inds_subset],
size_average=False,
beta=1,
)
# box_loss = self.box_reg_loss_func(box_regression[sampled_pos_inds_subset[:, None], map_inds],
# regression_targets[sampled_pos_inds_subset])
box_loss = box_loss / labels.numel()
return classification_loss, box_loss
def cat_boxlist_with_keypoints(boxlists):
assert all(boxlist.has_field("keypoints") for boxlist in boxlists)
kp = [boxlist.get_field("keypoints").keypoints for boxlist in boxlists]
kp = cat(kp, 0)
fields = boxlists[0].get_fields()
fields = [field for field in fields if field != "keypoints"]
boxlists = [boxlist.copy_with_fields(fields) for boxlist in boxlists]
boxlists = cat_boxlist(boxlists)
boxlists.add_field("keypoints", kp)
return boxlists
def concat_box_prediction_layers(self, box_regression):
box_regression_flattened = []
# for each feature level, permute the outputs to make them be in the
# same format as the labels. Note that the labels are computed for
# all feature levels concatenated, so we keep the same representation
# for the objectness and the box_regression
for box_regression_per_level in box_regression:
N, Ax4, H, W = box_regression_per_level.shape
A = Ax4 // 4
box_regression_per_level = self.permute_and_flatten(
box_regression_per_level, N, A, 4, H, W)
box_regression_flattened.append(box_regression_per_level)
# concatenate on the first dimension (representing the feature levels), to
# take into account the way the labels were generated (with all feature maps
# being concatenated as well)
box_regression = cat(box_regression_flattened, dim=1).reshape(-1, 4)
return box_regression