INNER CODE UNIT · Python

min_in

nv-tlabs/ATISS · scene_synthesis/losses/__init__.py:72

    min_in = inv_stdv * (centered_y - 1. / (num_classes - 1))
    cdf_min = torch.sigmoid(min_in)

    # log probability for edge case of 0 (before scaling)
    # equivalent: torch.log(torch.sigmoid(plus_in))
    log_cdf_plus = plus_in - F.softplus(plus_in)

    # log probability for edge case of 255 (before scaling)
    # equivalent: (1 - torch.sigmoid(min_in)).log()
    log_one_minus_cdf_min = -F.softplus(min_in)

    # probability for all other cases
    cdf_delta = cdf_plus - cdf_min

    mid_in = inv_stdv * centered_y
    # log probability in the center of the bin, to be used in extreme cases
    # (not actually used in our code)
    log_pdf_mid = mid_in - log_scales - 2. * F.softplus(mid_in)

View source record →