meshgpt pytorch Télécharger - meshgpt pytorch Téléchargement du code source

Implémentation de MeshGPT, génération SOTA Mesh à l'aide d'Attention, dans Pytorch

Ajoutera également un conditionnement de texte, pour un éventuel élément texte en 3D

Veuillez nous rejoindre si vous souhaitez collaborer avec d'autres pour reproduire ce travail

Mise à jour : Marcus a formé et téléchargé un modèle fonctionnel sur ? Visage câlin !

$ pip install meshgpt-pytorch

 import torch

from meshgpt_pytorch import (
    MeshAutoencoder ,
    MeshTransformer
)

# autoencoder

autoencoder = MeshAutoencoder (
    num_discrete_coors = 128
)

# mock inputs

vertices = torch . randn (( 2 , 121 , 3 ))            # (batch, num vertices, coor (3))
faces = torch . randint ( 0 , 121 , ( 2 , 64 , 3 ))      # (batch, num faces, vertices (3))

# make sure faces are padded with `-1` for variable lengthed meshes

# forward in the faces

loss = autoencoder (
    vertices = vertices ,
    faces = faces
)

loss . backward ()

# after much training...
# you can pass in the raw face data above to train a transformer to model this sequence of face vertices

transformer = MeshTransformer (
    autoencoder ,
    dim = 512 ,
    max_seq_len = 768
)

loss = transformer (
    vertices = vertices ,
    faces = faces
)

loss . backward ()

# after much training of transformer, you can now sample novel 3d assets

faces_coordinates , face_mask = transformer . generate ()

# (batch, num faces, vertices (3), coordinates (3)), (batch, num faces)
# now post process for the generated 3d asset

Pour la synthèse de formes 3D conditionnée par le texte, définissez simplement condition_on_text = True sur votre MeshTransformer , puis transmettez votre liste de descriptions comme argument de mot-clé texts

 transformer = MeshTransformer (
    autoencoder ,
    dim = 512 ,
    max_seq_len = 768 ,
    condition_on_text = True
)


loss = transformer (
    vertices = vertices ,
    faces = faces ,
    texts = [ 'a high chair' , 'a small teapot' ],
)

loss . backward ()

# after much training of transformer, you can now sample novel 3d assets conditioned on text

faces_coordinates , face_mask = transformer . generate (
    texts = [ 'a long table' ],
    cond_scale = 8. ,  # a cond_scale > 1. will enable classifier free guidance - can be placed anywhere from 3. - 10.
    remove_parallel_component = True # from https://arxiv.org/abs/2410.02416
)

Si vous souhaitez tokeniser des maillages, pour les utiliser dans votre transformateur multimodal, invoquez simplement .tokenize sur votre auto-encodeur (ou la même méthode sur l'instance d'entraînement de l'auto-encodeur pour le modèle lissé exponentiellement)

 mesh_token_ids = autoencoder . tokenize (
    vertices = vertices ,
    faces = faces
)

# (batch, num face vertices, residual quantized layer)

$ cp .env.sample .env

 @inproceedings { Siddiqui2023MeshGPTGT ,
    title   = { MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers } ,
    author  = { Yawar Siddiqui and Antonio Alliegro and Alexey Artemov and Tatiana Tommasi and Daniele Sirigatti and Vladislav Rosov and Angela Dai and Matthias Nie{ss}ner } ,
    year    = { 2023 } ,
    url     = { https://api.semanticscholar.org/CorpusID:265457242 }
}

 @inproceedings { dao2022flashattention ,
    title   = { Flash{A}ttention: Fast and Memory-Efficient Exact Attention with {IO}-Awareness } ,
    author  = { Dao, Tri and Fu, Daniel Y. and Ermon, Stefano and Rudra, Atri and R{'e}, Christopher } ,
    booktitle = { Advances in Neural Information Processing Systems } ,
    year    = { 2022 }
}

 @inproceedings { Leviathan2022FastIF ,
    title   = { Fast Inference from Transformers via Speculative Decoding } ,
    author  = { Yaniv Leviathan and Matan Kalman and Y. Matias } ,
    booktitle = { International Conference on Machine Learning } ,
    year    = { 2022 } ,
    url     = { https://api.semanticscholar.org/CorpusID:254096365 }
}

 @misc { yu2023language ,
    title   = { Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation } , 
    author  = { Lijun Yu and José Lezama and Nitesh B. Gundavarapu and Luca Versari and Kihyuk Sohn and David Minnen and Yong Cheng and Agrim Gupta and Xiuye Gu and Alexander G. Hauptmann and Boqing Gong and Ming-Hsuan Yang and Irfan Essa and David A. Ross and Lu Jiang } ,
    year    = { 2023 } ,
    eprint  = { 2310.05737 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}

 @article { Lee2022AutoregressiveIG ,
    title   = { Autoregressive Image Generation using Residual Quantization } ,
    author  = { Doyup Lee and Chiheon Kim and Saehoon Kim and Minsu Cho and Wook-Shin Han } ,
    journal = { 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) } ,
    year    = { 2022 } ,
    pages   = { 11513-11522 } ,
    url     = { https://api.semanticscholar.org/CorpusID:247244535 }
}

 @inproceedings { Katsch2023GateLoopFD ,
    title   = { GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling } ,
    author  = { Tobias Katsch } ,
    year    = { 2023 } ,
    url     = { https://api.semanticscholar.org/CorpusID:265018962 }
}