vis4d.op.loss.multi_pos_cross_entropy

Multi-positive cross entropy loss.

Functions

multi_pos_cross_entropy(pred, target, reducer)

Calculate multi-positive cross-entropy loss.

Classes

MultiPosCrossEntropyLoss([reducer])

Multi-positive cross entropy loss.

class MultiPosCrossEntropyLoss(reducer=<function identity_loss>)

Multi-positive cross entropy loss.

Used for appearance similiary learning in QDTrack.

Initialize a loss functor.

Parameters:

• reducer (LossReducer) – A function to aggregate the loss values into

• prediction (a single tensor value. It is commonly used for dense)

• loss. (tasks to merge pixel-wise loss to a final)

• Example:: –

  def mean_loss(loss: torch.Tensor) -> torch.Tensor:

  return loss.mean()

forward(pred, target, weight, avg_factor)

Multi-positive cross entropy loss.

Parameters:

• pred (Tensor) – Similarity scores before softmax. Shape [N, M]

• target (Tensor) – Target for each pair. Either one, meaning same identity or zero, meaning different identity. Shape [N, M]

• weight (Tensor) – The weight of loss for each prediction.

• avg_factor (float) – Averaging factor for the loss.

Returns:

Scalar loss value.

Return type:

Tensor

multi_pos_cross_entropy(pred, target, reducer)

Calculate multi-positive cross-entropy loss.

Return type:

Tensor