Source code for towhee.models.utils.weight_init

# Copyright 2021 Ross Wightman . All rights reserved.
# Licensed under the Apache License, Version 2.0 (the 'License');
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an 'AS IS' BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
# This code is modified by Zilliz.

import torch
import math
import warnings
from torch.nn.init import _calculate_fan_in_and_fan_out

def _no_grad_trunc_normal_(tensor, mean, std, a, b):
    # Cut & paste from PyTorch official master until it's in a few official releases - RW
    # Method based on
    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.',

    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
        l = norm_cdf((a - mean) / std)
        u = norm_cdf((b - mean) / std)

        # Uniformly fill tensor with values from [l, u], then translate to
        # [2l-1, 2u-1].
        tensor.uniform_(2 * l - 1, 2 * u - 1)

        # Use inverse cdf transform for normal distribution to get truncated
        # standard normal

        # Transform to proper mean, std
        tensor.mul_(std * math.sqrt(2.))

        # Clamp to ensure it's in the proper range
        tensor.clamp_(min=a, max=b)
        return tensor

[docs]def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.): # type: (Tensor, float, float, float, float) -> Tensor 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: an n-dimensional `torch.Tensor` mean: the mean of the normal distribution std: the standard deviation of the normal distribution a: the minimum cutoff value b: the maximum cutoff value Examples: >>> w = torch.empty(3, 5) >>> nn.init.trunc_normal_(w) """ return _no_grad_trunc_normal_(tensor, mean, std, a, b)
[docs]def variance_scaling_(tensor, scale=1.0, mode='fan_in', distribution='normal'): fan_in, fan_out = _calculate_fan_in_and_fan_out(tensor) if mode == 'fan_in': denom = fan_in elif mode == 'fan_out': denom = fan_out elif mode == 'fan_avg': denom = (fan_in + fan_out) / 2 variance = scale / denom if distribution == 'truncated_normal': # constant is stddev of standard normal truncated to (-2, 2) trunc_normal_(tensor, std=math.sqrt(variance) / .87962566103423978) elif distribution == 'normal': tensor.normal_(std=math.sqrt(variance)) elif distribution == 'uniform': bound = math.sqrt(3 * variance) tensor.uniform_(-bound, bound) else: raise ValueError(f'invalid distribution {distribution}')
[docs]def lecun_normal_(tensor): variance_scaling_(tensor, mode='fan_in', distribution='truncated_normal')