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, w, h), 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(generalized_box_iou(box_cxcywh_to_xyxy(src_boxes),
# box_cxcywh_to_xyxy(target_boxes)))
loss_giou = 1 - torch.diag(
generalized_box_iou(
box_convert(src_boxes, in_fmt="cxcywh", out_fmt="xyxy"),
box_convert(target_boxes, in_fmt="cxcywh", out_fmt="xyxy")))
losses["loss_giou"] = loss_giou.sum() / num_boxes
return losses
def forward(self, outputs, targets):
"""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 = (outputs["pred_logits"].flatten(0, 1).softmax(-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 ommitted.
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), box_cxcywh_to_xyxy(tgt_bbox))
cost_giou = -generalized_box_iou(
box_convert(out_bbox, in_fmt="cxcywh", out_fmt="xyxy"),
box_convert(tgt_bbox, in_fmt="cxcywh", out_fmt="xyxy"))
# 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]
def _evaluate_giou(target, pred):
"""
Evaluate generalized intersection over union (gIOU) for target from dataset and output prediction
from model.
"""
if pred["boxes"].shape[0] == 0:
# no box detected, 0 IOU
return torch.tensor(0.0, device=pred["boxes"].device)
return generalized_box_iou(target["boxes"], pred["boxes"]).diag().mean()
def test_gen_iou(self):
# Test Generalized IoU
boxes1 = torch.tensor([[0, 0, 100, 100], [0, 0, 50, 50], [200, 200, 300, 300]], dtype=torch.float)
boxes2 = torch.tensor([[0, 0, 100, 100], [0, 0, 50, 50], [200, 200, 300, 300]], dtype=torch.float)
# Expected gIoU matrix for these boxes
expected = torch.tensor([[1.0, 0.25, -0.7778], [0.25, 1.0, -0.8611],
[-0.7778, -0.8611, 1.0]])
out = ops.generalized_box_iou(boxes1, boxes2)
# Check if all elements of tensor are as expected.
assert out.size() == torch.Size([3, 3])
tolerance = 1e-4
assert ((out - expected).abs().max() < tolerance).item() is True
def gen_iou_check(box, expected, tolerance=1e-4):
out = ops.generalized_box_iou(box, box)
assert out.size() == expected.size()
assert ((out - expected).abs().max() < tolerance).item()
def gen_iou_check(box, expected, tolerance=1e-4):
out = ops.generalized_box_iou(box, box)
torch.testing.assert_close(out, expected, rtol=0.0, check_dtype=False, atol=tolerance)
def forward(self, inputs: Tensor, target: Tensor) -> Tensor:
return 1.0 - generalized_box_iou(inputs, target).diagonal()