Spaces:
Sleeping
Sleeping
| # SPDX-FileCopyrightText: Copyright (c) 2023 - 2025 NVIDIA CORPORATION & AFFILIATES. | |
| # SPDX-FileCopyrightText: All rights reserved. | |
| # SPDX-License-Identifier: Apache-2.0 | |
| # | |
| # 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 | |
| # | |
| # http://www.apache.org/licenses/LICENSE-2.0 | |
| # | |
| # Unless required by applicable law or agreed to in writing, software | |
| # distributed under the License is distributed on an "AS IS" BASIS, | |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| # See the License for the specific language governing permissions and | |
| # limitations under the License. | |
| import math | |
| import warnings | |
| import torch | |
| def _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 https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf | |
| def norm_cdf(x): | |
| # Computes standard normal cumulative distribution function | |
| return (1.0 + math.erf(x / math.sqrt(2.0))) / 2.0 | |
| 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, | |
| ) | |
| # 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 | |
| u1 = norm_cdf((a - mean) / std) | |
| u2 = norm_cdf((b - mean) / std) | |
| # Uniformly fill tensor with values from [u1, u2], then translate to | |
| # [2u1-1, 2u2-1]. | |
| tensor.uniform_(2 * u1 - 1, 2 * u2 - 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(2.0)) | |
| 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=0.0, std=1.0, a=-2.0, b=2.0): | |
| # type: (Tensor, float, float, float, float) -> Tensor | |
| r"""Cut & paste from timm master | |
| 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`. | |
| NOTE: this impl is similar to the PyTorch trunc_normal_, the bounds [a, b] are | |
| applied while sampling the normal with mean/std applied, therefore a, b args | |
| should be adjusted to match the range of mean, std args. | |
| """ | |
| with torch.no_grad(): | |
| return _trunc_normal_(tensor, mean, std, a, b) | |