def losses(self, predictions, proposals):
"""
Args:
predictions: return values of :meth:`forward()`.
proposals (list[Instances]): proposals that match the features that were used
to compute predictions. The fields ``proposal_boxes``, ``gt_boxes``,
``gt_classes`` are expected.
Returns:
Dict[str, Tensor]: dict of losses
"""
scores, proposal_deltas = predictions
gt_classes = (cat([p.gt_classes for p in proposals], dim=0)
if len(proposals) else torch.empty(0))
_log_classification_stats(scores, gt_classes)
# TODO: move the regression implementation to this class.
reg_losses = FastRCNNOutputs(
self.box2box_transform,
scores,
proposal_deltas,
proposals,
self.smooth_l1_beta,
self.box_reg_loss_type,
).box_reg_loss()
losses = {
"loss_cls": cross_entropy(scores, gt_classes, reduction="mean"),
"loss_box_reg": reg_losses,
}
return {k: v * self.loss_weight.get(k, 1.0) for k, v in losses.items()}
def softmax_cross_entropy_loss(self):
"""
Deprecated
"""
_log_classification_stats(self.pred_class_logits, self.gt_classes)
return cross_entropy(self.pred_class_logits,
self.gt_classes,
reduction="mean")
def losses(self, predictions, proposals):
"""
Args:
predictions: return values of :meth:`forward()`.
proposals (list[Instances]): proposals that match the features that were used
to compute predictions. The fields ``proposal_boxes``, ``gt_boxes``,
``gt_classes`` are expected.
Returns:
Dict[str, Tensor]: dict of losses
"""
scores, proposal_deltas = predictions
# parse classification outputs
gt_classes = (
cat([p.gt_classes for p in proposals], dim=0) if len(proposals) else torch.empty(0)
)
_log_classification_stats(scores, gt_classes)
# parse box regression outputs
if len(proposals):
proposal_boxes = cat([p.proposal_boxes.tensor for p in proposals], dim=0) # Nx4
assert not proposal_boxes.requires_grad, "Proposals should not require gradients!"
# If "gt_boxes" does not exist, the proposals must be all negative and
# should not be included in regression loss computation.
# Here we just use proposal_boxes as an arbitrary placeholder because its
# value won't be used in self.box_reg_loss().
gt_boxes = cat(
[(p.gt_boxes if p.has("gt_boxes") else p.proposal_boxes).tensor for p in proposals],
dim=0,
)
else:
proposal_boxes = gt_boxes = torch.empty((0, 4), device=proposal_deltas.device)
if self.use_sigmoid_ce:
loss_cls = self.sigmoid_cross_entropy_loss(scores, gt_classes)
else:
loss_cls = cross_entropy(scores, gt_classes, reduction="mean")
losses = {
"loss_cls": loss_cls,
"loss_box_reg": self.box_reg_loss(
proposal_boxes, gt_boxes, proposal_deltas, gt_classes
),
}
return {k: v * self.loss_weight.get(k, 1.0) for k, v in losses.items()}
