autoregressive diffusion pytorch

انتشار الانحدار الذاتي - Pytorch

تنفيذ البنية وراء إنشاء الصور بالانحدار التلقائي دون تكميم المتجهات في Pytorch

تم إصدار المستودع الرسمي هنا

طريق بديل

زهور أكسفورد على ارتفاع 96 ألف خطوة

ثَبَّتَ

$ pip install autoregressive-diffusion-pytorch

الاستخدام

 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

بالنسبة للصور التي يتم التعامل معها كسلسلة من الرموز المميزة (كما هو الحال في الورق)

 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

مدرب الصور

 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 ()

للحصول على إصدار مرتجل يستخدم مطابقة التدفق، ما عليك سوى استيراد ImageAutoregressiveFlow و AutoregressiveFlow بدلاً من ذلك

الباقي هو نفسه

السابق.

 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 ()

الاستشهادات

 @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 }
}