embeddings.py

# Copyright 2022 The HuggingFace Team. 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
#
#     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 numpy as np
import torch
from torch import nn


def get_timestep_embedding(
    timesteps, embedding_dim, flip_sin_to_cos=False, downscale_freq_shift=1, scale=1, max_period=10000
):
    """
    This matches the implementation in Denoising Diffusion Probabilistic Models: Create sinusoidal timestep embeddings.

    :param timesteps: a 1-D Tensor of N indices, one per batch element.
                      These may be fractional.
    :param embedding_dim: the dimension of the output. :param max_period: controls the minimum frequency of the
    embeddings. :return: an [N x dim] Tensor of positional embeddings.
    """
    assert len(timesteps.shape) == 1, "Timesteps should be a 1d-array"

    half_dim = embedding_dim // 2

    emb_coeff = -math.log(max_period) / (half_dim - downscale_freq_shift)
    emb = torch.arange(half_dim, dtype=torch.float32, device=timesteps.device)
    emb = torch.exp(emb * emb_coeff)
    emb = timesteps[:, None].float() * emb[None, :]

    # scale embeddings
    emb = scale * emb

    # concat sine and cosine embeddings
    emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=-1)

    # flip sine and cosine embeddings
    if flip_sin_to_cos:
        emb = torch.cat([emb[:, half_dim:], emb[:, :half_dim]], dim=-1)

    # zero pad
    if embedding_dim % 2 == 1:
        emb = torch.nn.functional.pad(emb, (0, 1, 0, 0))
    return emb


# unet_sde_score_estimation.py
class GaussianFourierProjection(nn.Module):
    """Gaussian Fourier embeddings for noise levels."""

    def __init__(self, embedding_size=256, scale=1.0):
        super().__init__()
        self.W = nn.Parameter(torch.randn(embedding_size) * scale, requires_grad=False)

    def forward(self, x):
        x_proj = x[:, None] * self.W[None, :] * 2 * np.pi
        return torch.cat([torch.sin(x_proj), torch.cos(x_proj)], dim=-1)