quaterion.loss.fast_ap_loss module

class FastAPLoss(num_bins: int | None = 10)

Bases: GroupLoss

FastAP Loss

Adaptation from https://github.com/kunhe/FastAP-metric-learning.

Further information:

https://cs-people.bu.edu/fcakir/papers/fastap_cvpr2019.pdf. “Deep Metric Learning to Rank” Fatih Cakir(*), Kun He(*), Xide Xia, Brian Kulis, and Stan Sclaroff IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

Parameters:

num_bins – The number of soft histogram bins for calculating average precision. The paper suggests using 10.

forward(embeddings: Tensor, groups: Tensor) → Tensor

Compute loss value.

Parameters:

• embeddings – shape: (batch_size, vector_length) - Batch of embeddings.

• groups – shape: (batch_size,) - Batch of labels associated with embeddings.

Returns:

Tensor – Scalar loss value.

get_config_dict() → Dict[str, Any]

Config used in saving and loading purposes.

Config object has to be JSON-serializable.

Returns:

Dict[str, Any] – JSON-serializable dict of params

training: bool