autoregressive diffusion pytorch

Авторегрессионная диффузия — Пайторч

Реализация архитектуры авторегрессионной генерации изображений без векторного квантования в Pytorch

Официальный репозиторий выложен здесь.

Альтернативный маршрут

Оксфордские цветы на 96 тысячах шагов

Установить

$ pip install autoregressive-diffusion-pytorch

Использование

 import torch
from autoregressive_diffusion_pytorch import AutoregressiveDiffusion

model = AutoregressiveDiffusion (
    dim_input = 512 ,
    dim = 1024 ,
    max_seq_len = 32 ,
    depth = 8 ,
    mlp_depth = 3 ,
    mlp_width = 1024
)

seq = torch . randn ( 3 , 32 , 512 )

loss = model ( seq )
loss . backward ()

sampled = model . sample ( batch_size = 3 )

assert sampled . shape == seq . shape

Для изображений, рассматриваемых как последовательность токенов (как на бумаге)

 import torch
from autoregressive_diffusion_pytorch import ImageAutoregressiveDiffusion

model = ImageAutoregressiveDiffusion (
    model = dict (
        dim = 1024 ,
        depth = 12 ,
        heads = 12 ,
    ),
    image_size = 64 ,
    patch_size = 8
)

images = torch . randn ( 3 , 3 , 64 , 64 )

loss = model ( images )
loss . backward ()

sampled = model . sample ( batch_size = 3 )

assert sampled . shape == images . shape

Тренажер изображений

 import torch

from autoregressive_diffusion_pytorch import (
    ImageDataset ,
    ImageAutoregressiveDiffusion ,
    ImageTrainer
)

dataset = ImageDataset (
    '/path/to/your/images' ,
    image_size = 128
)

model = ImageAutoregressiveDiffusion (
    model = dict (
        dim = 512
    ),
    image_size = 128 ,
    patch_size = 16
)

trainer = ImageTrainer (
    model = model ,
    dataset = dataset
)

trainer ()

Для импровизированной версии, использующей сопоставление потоков, просто вместо этого импортируйте ImageAutoregressiveFlow и AutoregressiveFlow

Остальное то же самое

бывший.

 import torch

from autoregressive_diffusion_pytorch import (
    ImageDataset ,
    ImageTrainer ,
    ImageAutoregressiveFlow ,
)

dataset = ImageDataset (
    '/path/to/your/images' ,
    image_size = 128
)

model = ImageAutoregressiveFlow (
    model = dict (
        dim = 512
    ),
    image_size = 128 ,
    patch_size = 16
)

trainer = ImageTrainer (
    model = model ,
    dataset = dataset
)

trainer ()

Цитаты

 @article { Li2024AutoregressiveIG ,
    title   = { Autoregressive Image Generation without Vector Quantization } ,
    author  = { Tianhong Li and Yonglong Tian and He Li and Mingyang Deng and Kaiming He } ,
    journal = { ArXiv } ,
    year    = { 2024 } ,
    volume  = { abs/2406.11838 } ,
    url     = { https://api.semanticscholar.org/CorpusID:270560593 }
}

 @article { Wu2023ARDiffusionAD ,
    title     = { AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation } ,
    author    = { Tong Wu and Zhihao Fan and Xiao Liu and Yeyun Gong and Yelong Shen and Jian Jiao and Haitao Zheng and Juntao Li and Zhongyu Wei and Jian Guo and Nan Duan and Weizhu Chen } ,
    journal   = { ArXiv } ,
    year      = { 2023 } ,
    volume    = { abs/2305.09515 } ,
    url       = { https://api.semanticscholar.org/CorpusID:258714669 }
}

 @article { Karras2022ElucidatingTD ,
    title   = { Elucidating the Design Space of Diffusion-Based Generative Models } ,
    author  = { Tero Karras and Miika Aittala and Timo Aila and Samuli Laine } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2206.00364 } ,
    url     = { https://api.semanticscholar.org/CorpusID:249240415 }
}

 @article { Liu2022FlowSA ,
    title   = { Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow } ,
    author  = { Xingchao Liu and Chengyue Gong and Qiang Liu } ,
    journal = { ArXiv } ,
    year    = { 2022 } ,
    volume  = { abs/2209.03003 } ,
    url     = { https://api.semanticscholar.org/CorpusID:252111177 }
}

 @article { Esser2024ScalingRF ,
    title   = { Scaling Rectified Flow Transformers for High-Resolution Image Synthesis } ,
    author  = { Patrick Esser and Sumith Kulal and A. Blattmann and Rahim Entezari and Jonas Muller and Harry Saini and Yam Levi and Dominik Lorenz and Axel Sauer and Frederic Boesel and Dustin Podell and Tim Dockhorn and Zion English and Kyle Lacey and Alex Goodwin and Yannik Marek and Robin Rombach } ,
    journal = { ArXiv } ,
    year    = { 2024 } ,
    volume  = { abs/2403.03206 } ,
    url     = { https://api.semanticscholar.org/CorpusID:268247980 }
}