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) if not self.use_focal_loss else \
frcnn_focal_loss(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 = box_loss / labels.numel()
return classification_loss, box_loss
def __call__(self, anchors, objectness, box_regression, targets):
"""
Arguments:
anchors (list[BoxList])
objectness (list[Tensor])
box_regression (list[Tensor])
targets (list[BoxList])
Returns:
objectness_loss (Tensor)
box_loss (Tensor
"""
anchors = [
cat_boxlist(anchors_per_image) for anchors_per_image in anchors
]
labels, regression_targets = self.prepare_targets(anchors, targets)
sampled_pos_inds, sampled_neg_inds = self.fg_bg_sampler(labels)
sampled_pos_inds = torch.nonzero(torch.cat(sampled_pos_inds,
dim=0)).squeeze(1)
sampled_neg_inds = torch.nonzero(torch.cat(sampled_neg_inds,
dim=0)).squeeze(1)
sampled_inds = torch.cat([sampled_pos_inds, sampled_neg_inds], dim=0)
objectness, box_regression = \
concat_box_prediction_layers(objectness, box_regression)
objectness = objectness.squeeze()
labels = torch.cat(labels, dim=0)
regression_targets = torch.cat(regression_targets, dim=0)
box_loss = smooth_l1_loss(
box_regression[sampled_pos_inds],
regression_targets[sampled_pos_inds],
beta=1.0 / 9,
size_average=False,
) / (sampled_inds.numel())
objectness_loss = F.binary_cross_entropy_with_logits(
objectness[sampled_inds], labels[sampled_inds]
) if not self.use_focal_loss else \
rpn_focal_loss(
objectness[sampled_inds], labels[sampled_inds]
)
return objectness_loss, box_loss
def __call__(self, anchors, box_cls, box_regression, targets):
"""
Arguments:
anchors (list[BoxList])
box_cls (list[Tensor])
box_regression (list[Tensor])
targets (list[BoxList])
Returns:
retinanet_cls_loss (Tensor)
retinanet_regression_loss (Tensor
"""
anchors = [
cat_boxlist(anchors_per_image) for anchors_per_image in anchors
]
labels, regression_targets = self.prepare_targets(anchors, targets)
N = len(labels)
box_cls, box_regression = \
concat_box_prediction_layers(box_cls, box_regression)
labels = jt.contrib.concat(labels, dim=0)
regression_targets = jt.contrib.concat(regression_targets, dim=0)
pos_inds = jt.nonzero(labels > 0).squeeze(1)
retinanet_regression_loss = smooth_l1_loss(
box_regression[pos_inds],
regression_targets[pos_inds],
beta=self.bbox_reg_beta,
size_average=False,
) / (max(1,
pos_inds.numel() * self.regress_norm))
labels = labels.int()
retinanet_cls_loss = self.box_cls_loss_func(
box_cls, labels) / (pos_inds.numel() + N)
return retinanet_cls_loss, retinanet_regression_loss