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>)[source]

Multi-positive cross entropy loss.

Used for appearance similiary learning in QDTrack.

forward(pred, target, weight, avg_factor)[source]

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)[source]

Calculate multi-positive cross-entropy loss.

Return type:

Tensor