def loss_boxes(self, outputs, targets, indices, num_boxes):
"""Compute the losses related to the bounding boxes, the L1 regression loss and
the GIoU loss
targets dicts must contain the key "boxes" containing a tensor of dim
[nb_target_boxes, 4]
The target boxes are expected in format (center_x, center_y, h, w),
normalized by the image size.
"""
assert "pred_boxes" in outputs
idx = self._get_src_permutation_idx(indices)
src_boxes = outputs["pred_boxes"][idx]
target_boxes = torch.cat(
[t["boxes"][i] for t, (_, i) in zip(targets, indices)], dim=0)
loss_bbox = F.l1_loss(src_boxes, target_boxes, reduction="none")
losses = {}
losses["loss_bbox"] = loss_bbox.sum() / num_boxes
loss_giou = 1 - torch.diag(
box_ops.generalized_box_iou(
box_ops.box_cxcywh_to_xyxy(src_boxes).float(),
box_ops.box_cxcywh_to_xyxy(target_boxes),
))
losses["loss_giou"] = loss_giou.sum() / num_boxes
return losses
def forward(self, outputs: Dict[str, Tensor], target_sizes: Tensor):
out_logits, out_bbox = outputs["pred_logits"], outputs["pred_boxes"]
assert len(out_logits) == len(target_sizes)
assert target_sizes.shape[1] == 2
prob = F.softmax(out_logits, -1)
scores, labels = prob[..., :-1].max(-1)
# convert to [x0, y0, x1, y1] format
from mmf.utils.box_ops import box_cxcywh_to_xyxy
boxes = box_cxcywh_to_xyxy(out_bbox)
# and from relative [0, 1] to absolute [0, height] coordinates
img_h, img_w = target_sizes.unbind(1)
scale_fct = torch.stack([img_w, img_h, img_w, img_h], dim=1)
boxes = boxes * scale_fct[:, None, :]
results = [{
"scores": s,
"labels": l,
"boxes": b
} for s, l, b in zip(scores, labels, boxes)]
if "attr_logits" in outputs:
assert len(outputs["attr_logits"]) == len(results)
attr_scores, attr_labels = outputs["attr_logits"].max(-1)
for idx, r in enumerate(results):
r["attr_scores"] = attr_scores[idx]
r["attr_labels"] = attr_labels[idx]
return results
def forward(self, outputs: Dict[str, Tensor], targets: List[Dict[str,
Tensor]]):
""" Performs the matching
Params:
outputs: This is a dict that contains at least these entries:
"pred_logits": Tensor of dim [batch_size, num_queries, num_classes]
with the classification logits
"pred_boxes": Tensor of dim [batch_size, num_queries, 4] with the
predicted box coordinates
targets: This is a list of targets (len(targets) = batch_size), where each
target is a dict containing:
"labels": Tensor of dim [num_target_boxes] (where num_target_boxes is
the number of ground-truth objects in the target) containing the
class labels
"boxes": Tensor of dim [num_target_boxes, 4] containing the target box
coordinates
Returns:
A list of size batch_size, containing tuples of (index_i, index_j) where:
- index_i is the indices of the selected predictions (in order)
- index_j is the indices of the corresponding selected targets (in
order)
For each batch element, it holds:
len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
"""
bs, num_queries = outputs["pred_logits"].shape[:2]
# We flatten to compute the cost matrices in a batch
out_prob = self.norm(outputs["pred_logits"].flatten(
0, 1)) # [batch_size * num_queries, num_classes]
out_bbox = outputs["pred_boxes"].flatten(
0, 1) # [batch_size * num_queries, 4]
# Also concat the target labels and boxes
tgt_ids = torch.cat([v["labels"] for v in targets])
tgt_bbox = torch.cat([v["boxes"] for v in targets])
# Compute the classification cost. Contrary to the loss, we don't use the NLL,
# but approximate it in 1 - proba[target class].
# The 1 is a constant that doesn't change the matching, it can be omitted.
cost_class = -out_prob[:, tgt_ids]
# Compute the L1 cost between boxes
cost_bbox = torch.cdist(out_bbox, tgt_bbox, p=1)
# Compute the giou cost betwen boxes
cost_giou = -generalized_box_iou(
box_cxcywh_to_xyxy(out_bbox).float(), box_cxcywh_to_xyxy(tgt_bbox))
# Final cost matrix
C = (self.cost_bbox * cost_bbox + self.cost_class * cost_class +
self.cost_giou * cost_giou)
C = C.view(bs, num_queries, -1).cpu()
sizes = [len(v["boxes"]) for v in targets]
indices = [
linear_sum_assignment(c[i])
for i, c in enumerate(C.split(sizes, -1))
]
return [(
torch.as_tensor(i, dtype=torch.int64),
torch.as_tensor(j, dtype=torch.int64),
) for i, j in indices]