meshgpt pytorch herunterladen - meshgpt pytorch Quellcode herunterladen

Wird auch eine Textkonditionierung für eventuelle Text-zu-3D-Assets hinzufügen

Bitte treten Sie bei, wenn Sie daran interessiert sind, mit anderen zusammenzuarbeiten, um diese Arbeit zu reproduzieren

Update: Marcus hat trainiert und ein funktionierendes Modell hochgeladen? Umarmendes Gesicht!

$ 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

Für eine textbedingte 3D-Formsynthese setzen Sie einfach condition_on_text = True auf Ihrem MeshTransformer und übergeben dann Ihre Beschreibungsliste als texts Schlüsselwortargument

 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
)

Wenn Sie Netze zur Verwendung in Ihrem multimodalen Transformator tokenisieren möchten, rufen Sie einfach .tokenize auf Ihrem Autoencoder auf (oder dieselbe Methode auf der Autoencoder-Trainer-Instanz für das exponentiell geglättete Modell).

 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 }
}