File size: 2,327 Bytes
18dd6ad |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
"""Modified from https://github.com/rwightman/pytorch-image-
models/blob/master/timm/models/layers/drop.py."""
import math
import warnings
import torch
def _no_grad_trunc_normal_(tensor, mean, std, a, b):
"""Reference: https://people.sc.fsu.edu/~jburkardt/presentations
/truncated_normal.pdf"""
def norm_cdf(x):
# Computes standard normal cumulative distribution function
return (1. + math.erf(x / math.sqrt(2.))) / 2.
if (mean < a - 2 * std) or (mean > b + 2 * std):
warnings.warn(
'mean is more than 2 std from [a, b] in nn.init.trunc_normal_. '
'The distribution of values may be incorrect.',
stacklevel=2)
with torch.no_grad():
# Values are generated by using a truncated uniform distribution and
# then using the inverse CDF for the normal distribution.
# Get upper and lower cdf values
lower_bound = norm_cdf((a - mean) / std)
upper_bound = norm_cdf((b - mean) / std)
# Uniformly fill tensor with values from [l, u], then translate to
# [2l-1, 2u-1].
tensor.uniform_(2 * lower_bound - 1, 2 * upper_bound - 1)
# Use inverse cdf transform for normal distribution to get truncated
# standard normal
tensor.erfinv_()
# Transform to proper mean, std
tensor.mul_(std * math.sqrt(2.))
tensor.add_(mean)
# Clamp to ensure it's in the proper range
tensor.clamp_(min=a, max=b)
return tensor
def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
r"""Fills the input Tensor with values drawn from a truncated
normal distribution. The values are effectively drawn from the
normal distribution :math:`\mathcal{N}(\text{mean}, \text{std}^2)`
with values outside :math:`[a, b]` redrawn until they are within
the bounds. The method used for generating the random values works
best when :math:`a \leq \text{mean} \leq b`.
Args:
tensor (``torch.Tensor``): an n-dimensional `torch.Tensor`
mean (float): the mean of the normal distribution
std (float): the standard deviation of the normal distribution
a (float): the minimum cutoff value
b (float): the maximum cutoff value
"""
return _no_grad_trunc_normal_(tensor, mean, std, a, b)
|