torchsig.models.spectrogram_models.detr.criterion.get_uncertain_point_coords_with_randomness

torchsig.models.spectrogram_models.detr.criterion.get_uncertain_point_coords_with_randomness(coarse_logits, uncertainty_func, num_points, oversample_ratio, importance_sample_ratio)[source]
Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The unceratinties

are calculated for each point using ‘uncertainty_func’ function that takes point’s logit prediction as input.

See PointRend paper for details. :param coarse_logits: A tensor of shape (N, C, Hmask, Wmask) or (N, 1, Hmask, Wmask) for

class-specific or class-agnostic prediction.

Parameters:

  • uncertainty_func – A function that takes a Tensor of shape (N, C, P) or (N, 1, P) that contains logit predictions for P points and returns their uncertainties as a Tensor of shape (N, 1, P).

  • num_points (int) – The number of points P to sample.

  • oversample_ratio (int) – Oversampling parameter.

  • importance_sample_ratio (float) – Ratio of points that are sampled via importnace sampling.

Returns:

A tensor of shape (N, P, 2) that contains the coordinates of P

sampled points.

Return type:

point_coords (Tensor)