146 lines
5.2 KiB
Python
Executable File
146 lines
5.2 KiB
Python
Executable File
# Modified from Meta DiT
|
|
|
|
# This source code is licensed under the license found in the
|
|
# LICENSE file in the root directory of this source tree.
|
|
# --------------------------------------------------------
|
|
# References:
|
|
# DiT: https://github.com/facebookresearch/DiT/tree/main
|
|
# GLIDE: https://github.com/openai/glide-text2im
|
|
# MAE: https://github.com/facebookresearch/mae/blob/main/models_mae.py
|
|
# --------------------------------------------------------
|
|
|
|
|
|
import math
|
|
|
|
import numpy as np
|
|
import torch
|
|
from torch import nn
|
|
|
|
|
|
class TimestepEmbedder(nn.Module):
|
|
"""
|
|
Embeds scalar timesteps into vector representations.
|
|
"""
|
|
|
|
def __init__(self, hidden_size, frequency_embedding_size=256):
|
|
super().__init__()
|
|
self.mlp = nn.Sequential(
|
|
nn.Linear(frequency_embedding_size, hidden_size, bias=True),
|
|
nn.SiLU(),
|
|
nn.Linear(hidden_size, hidden_size, bias=True),
|
|
)
|
|
self.frequency_embedding_size = frequency_embedding_size
|
|
|
|
@staticmethod
|
|
def timestep_embedding(t, dim, max_period=10000):
|
|
"""
|
|
Create sinusoidal timestep embeddings.
|
|
:param t: a 1-D Tensor of N indices, one per batch element.
|
|
These may be fractional.
|
|
:param dim: the dimension of the output.
|
|
:param max_period: controls the minimum frequency of the embeddings.
|
|
:return: an (N, D) Tensor of positional embeddings.
|
|
"""
|
|
# https://github.com/openai/glide-text2im/blob/main/glide_text2im/nn.py
|
|
half = dim // 2
|
|
freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(
|
|
device=t.device
|
|
)
|
|
args = t[:, None].float() * freqs[None]
|
|
embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
|
|
if dim % 2:
|
|
embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
|
|
return embedding
|
|
|
|
def forward(self, t):
|
|
t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
|
|
t_emb = self.mlp(t_freq)
|
|
return t_emb
|
|
|
|
|
|
class LabelEmbedder(nn.Module):
|
|
"""
|
|
Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.
|
|
"""
|
|
|
|
def __init__(self, num_classes, hidden_size, dropout_prob):
|
|
super().__init__()
|
|
use_cfg_embedding = dropout_prob > 0
|
|
self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
|
|
self.num_classes = num_classes
|
|
self.dropout_prob = dropout_prob
|
|
|
|
def token_drop(self, labels, force_drop_ids=None):
|
|
"""
|
|
Drops labels to enable classifier-free guidance.
|
|
"""
|
|
if force_drop_ids is None:
|
|
drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
|
|
else:
|
|
drop_ids = force_drop_ids == 1
|
|
labels = torch.where(drop_ids, self.num_classes, labels)
|
|
return labels
|
|
|
|
def forward(self, labels, train, force_drop_ids=None):
|
|
use_dropout = self.dropout_prob > 0
|
|
if (train and use_dropout) or (force_drop_ids is not None):
|
|
labels = self.token_drop(labels, force_drop_ids)
|
|
embeddings = self.embedding_table(labels)
|
|
return embeddings
|
|
|
|
|
|
#################################################################################
|
|
# Sine/Cosine Positional Embedding Functions #
|
|
#################################################################################
|
|
# https://github.com/facebookresearch/mae/blob/main/util/pos_embed.py
|
|
|
|
|
|
def get_2d_sincos_pos_embed(embed_dim, grid_size, cls_token=False, extra_tokens=0):
|
|
"""
|
|
grid_size: int of the grid height and width
|
|
return:
|
|
pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/ or w/o cls_token)
|
|
"""
|
|
grid_h = np.arange(grid_size, dtype=np.float32)
|
|
grid_w = np.arange(grid_size, dtype=np.float32)
|
|
grid = np.meshgrid(grid_w, grid_h) # here w goes first
|
|
grid = np.stack(grid, axis=0)
|
|
|
|
grid = grid.reshape([2, 1, grid_size, grid_size])
|
|
pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
|
|
if cls_token and extra_tokens > 0:
|
|
pos_embed = np.concatenate([np.zeros([extra_tokens, embed_dim]), pos_embed], axis=0)
|
|
return pos_embed
|
|
|
|
|
|
def get_2d_sincos_pos_embed_from_grid(embed_dim, grid):
|
|
assert embed_dim % 2 == 0
|
|
|
|
# use half of dimensions to encode grid_h
|
|
emb_h = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[0]) # (H*W, D/2)
|
|
emb_w = get_1d_sincos_pos_embed_from_grid(embed_dim // 2, grid[1]) # (H*W, D/2)
|
|
|
|
emb = np.concatenate([emb_h, emb_w], axis=1) # (H*W, D)
|
|
return emb
|
|
|
|
|
|
def get_1d_sincos_pos_embed_from_grid(embed_dim, pos):
|
|
"""
|
|
embed_dim: output dimension for each position
|
|
pos: a list of positions to be encoded: size (M,)
|
|
out: (M, D)
|
|
"""
|
|
assert embed_dim % 2 == 0
|
|
omega = np.arange(embed_dim // 2, dtype=np.float64)
|
|
omega /= embed_dim / 2.0
|
|
omega = 1.0 / 10000**omega # (D/2,)
|
|
|
|
pos = pos.reshape(-1) # (M,)
|
|
out = np.einsum("m,d->md", pos, omega) # (M, D/2), outer product
|
|
|
|
emb_sin = np.sin(out) # (M, D/2)
|
|
emb_cos = np.cos(out) # (M, D/2)
|
|
|
|
emb = np.concatenate([emb_sin, emb_cos], axis=1) # (M, D)
|
|
return emb
|