siren pytorch

Pytorch의 사이렌

SIREN의 Pytorch 구현 - 주기적 활성화 기능을 사용한 암시적 신경 표현

설치하다

$ pip install siren-pytorch

용법

SIREN 기반 다층 신경망

 import torch
from torch import nn
from siren_pytorch import SirenNet

net = SirenNet (
    dim_in = 2 ,                        # input dimension, ex. 2d coor
    dim_hidden = 256 ,                  # hidden dimension
    dim_out = 3 ,                       # output dimension, ex. rgb value
    num_layers = 5 ,                    # number of layers
    final_activation = nn . Sigmoid (),   # activation of final layer (nn.Identity() for direct output)
    w0_initial = 30.                   # different signals may require different omega_0 in the first layer - this is a hyperparameter
)

coor = torch . randn ( 1 , 2 )
net ( coor ) # (1, 3) <- rgb value

SIREN 레이어 1개

 import torch
from siren_pytorch import Siren

neuron = Siren (
    dim_in = 3 ,
    dim_out = 256
)

coor = torch . randn ( 1 , 3 )
neuron ( coor ) # (1, 256)

사인 활성화( torch.sin 주위의 래퍼)

 import torch
from siren_pytorch import Sine

act = Sine ( 1. )
coor = torch . randn ( 1 , 2 )
act ( coor )

지정된 SirenNet 에서 지정된 높이와 너비의 특정 이미지를 학습한 후 이후에 생성하는 래퍼입니다.

 import torch
from torch import nn
from siren_pytorch import SirenNet , SirenWrapper

net = SirenNet (
    dim_in = 2 ,                        # input dimension, ex. 2d coor
    dim_hidden = 256 ,                  # hidden dimension
    dim_out = 3 ,                       # output dimension, ex. rgb value
    num_layers = 5 ,                    # number of layers
    w0_initial = 30.                   # different signals may require different omega_0 in the first layer - this is a hyperparameter
)

wrapper = SirenWrapper (
    net ,
    image_width = 256 ,
    image_height = 256
)

img = torch . randn ( 1 , 3 , 256 , 256 )
loss = wrapper ( img )
loss . backward ()

# after much training ...
# simply invoke the wrapper without passing in anything

pred_img = wrapper () # (1, 3, 256, 256) 

잠재 코드를 이용한 변조

새로운 논문에서는 잠재 코드로 사이렌을 조정하는 가장 좋은 방법은 변조기 피드포워드 네트워크를 통해 잠재 벡터를 전달하는 것이라고 제안합니다. 여기서 각 레이어의 숨겨진 상태는 사이렌의 해당 레이어와 요소별로 곱해집니다.

SirenWrapper 에서 latent_dim 추가 키워드를 설정하면 간단히 사용할 수 있습니다.

 import torch
from torch import nn
from siren_pytorch import SirenNet , SirenWrapper

net = SirenNet (
    dim_in = 2 ,                        # input dimension, ex. 2d coor
    dim_hidden = 256 ,                  # hidden dimension
    dim_out = 3 ,                       # output dimension, ex. rgb value
    num_layers = 5 ,                    # number of layers
    w0_initial = 30.                   # different signals may require different omega_0 in the first layer - this is a hyperparameter
)

wrapper = SirenWrapper (
    net ,
    latent_dim = 512 ,
    image_width = 256 ,
    image_height = 256
)

latent = nn . Parameter ( torch . zeros ( 512 ). normal_ ( 0 , 1e-2 ))
img = torch . randn ( 1 , 3 , 256 , 256 )

loss = wrapper ( img , latent = latent )
loss . backward ()

# after much training ...
# simply invoke the wrapper without passing in anything

pred_img = wrapper ( latent = latent ) # (1, 3, 256, 256) 

인용

 @misc { sitzmann2020implicit ,
    title   = { Implicit Neural Representations with Periodic Activation Functions } ,
    author  = { Vincent Sitzmann and Julien N. P. Martel and Alexander W. Bergman and David B. Lindell and Gordon Wetzstein } ,
    year    = { 2020 } ,
    eprint  = { 2006.09661 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}

 @misc { mehta2021modulated ,
    title   = { Modulated Periodic Activations for Generalizable Local Functional Representations } , 
    author  = { Ishit Mehta and Michaël Gharbi and Connelly Barnes and Eli Shechtman and Ravi Ramamoorthi and Manmohan Chandraker } ,
    year    = { 2021 } ,
    eprint  = { 2104.03960 } ,
    archivePrefix = { arXiv } ,
    primaryClass = { cs.CV }
}