import torch
from models import BaseVAE
from torch import nn
from torch.nn import functional as F
from .types_ import *
from math import exp
class MSSIMVAE(BaseVAE):
def __init__(self,
in_channels: int,
latent_dim: int,
hidden_dims: List = None,
window_size: int = 11,
size_average: bool = True,
**kwargs) -> None:
super(MSSIMVAE, self).__init__()
self.latent_dim = latent_dim
self.in_channels = in_channels
modules = []
if hidden_dims is None:
hidden_dims = [32, 64, 128, 256, 512]
# Build Encoder
for h_dim in hidden_dims:
modules.append(
nn.Sequential(
nn.Conv2d(in_channels, out_channels=h_dim,
kernel_size= 3, stride= 2, padding = 1),
nn.BatchNorm2d(h_dim),
nn.LeakyReLU())
)
in_channels = h_dim
self.encoder = nn.Sequential(*modules)
self.fc_mu = nn.Linear(hidden_dims[-1]*4, latent_dim)
self.fc_var = nn.Linear(hidden_dims[-1]*4, latent_dim)
# Build Decoder
modules = []
self.decoder_input = nn.Linear(latent_dim, hidden_dims[-1] * 4)
hidden_dims.reverse()
for i in range(len(hidden_dims) - 1):
modules.append(
nn.Sequential(
nn.ConvTranspose2d(hidden_dims[i],
hidden_dims[i + 1],
kernel_size=3,
stride = 2,
padding=1,
output_padding=1),
nn.BatchNorm2d(hidden_dims[i + 1]),
nn.LeakyReLU())
)
self.decoder = nn.Sequential(*modules)
self.final_layer = nn.Sequential(
nn.ConvTranspose2d(hidden_dims[-1],
hidden_dims[-1],
kernel_size=3,
stride=2,
padding=1,
output_padding=1),
nn.BatchNorm2d(hidden_dims[-1]),
nn.LeakyReLU(),
nn.Conv2d(hidden_dims[-1], out_channels= 3,
kernel_size= 3, padding= 1),
nn.Tanh())
self.mssim_loss = MSSIM(self.in_channels,
window_size,
size_average)
def encode(self, input: Tensor) -> List[Tensor]:
"""
Encodes the input by passing through the encoder network
and returns the latent codes.
:param input: (Tensor) Input tensor to encoder [N x C x H x W]
:return: (Tensor) List of latent codes
"""
result = self.encoder(input)
result = torch.flatten(result, start_dim=1)
# Split the result into mu and var components
# of the latent Gaussian distribution
mu = self.fc_mu(result)
log_var = self.fc_var(result)
return [mu, log_var]
def decode(self, z: Tensor) -> Tensor:
"""
Maps the given latent codes
onto the image space.
:param z: (Tensor) [B x D]
:return: (Tensor) [B x C x H x W]
"""
result = self.decoder_input(z)
result = result.view(-1, 512, 2, 2)
result = self.decoder(result)
result = self.final_layer(result)
return result
def reparameterize(self, mu: Tensor, logvar: Tensor) -> Tensor:
"""
Reparameterization trick to sample from N(mu, var) from
N(0,1).
:param mu: (Tensor) Mean of the latent Gaussian [B x D]
:param logvar: (Tensor) Standard deviation of the latent Gaussian [B x D]
:return: (Tensor) [B x D]
"""
std = torch.exp(0.5 * logvar)
eps = torch.randn_like(std)
return eps * std + mu
def forward(self, input: Tensor, **kwargs) -> List[Tensor]:
mu, log_var = self.encode(input)
z = self.reparameterize(mu, log_var)
return [self.decode(z), input, mu, log_var]
def loss_function(self,
*args: Any,
**kwargs) -> dict:
"""
Computes the VAE loss function.
KL(N(\mu, \sigma), N(0, 1)) = \log \frac{1}{\sigma} + \frac{\sigma^2 + \mu^2}{2} - \frac{1}{2}
:param args:
:param kwargs:
:return:
"""
recons = args[0]
input = args[1]
mu = args[2]
log_var = args[3]
kld_weight = kwargs['M_N'] # Account for the minibatch samples from the dataset
recons_loss = self.mssim_loss(recons, input)
kld_loss = torch.mean(-0.5 * torch.sum(1 + log_var - mu ** 2 - log_var.exp(), dim = 1), dim = 0)
loss = recons_loss + kld_weight * kld_loss
return {'loss': loss, 'Reconstruction_Loss':recons_loss, 'KLD':-kld_loss}
def sample(self,
num_samples:int,
current_device: int, **kwargs) -> Tensor:
"""
Samples from the latent space and return the corresponding
image space map.
:param num_samples: (Int) Number of samples
:param current_device: (Int) Device to run the model
:return: (Tensor)
"""
z = torch.randn(num_samples,
self.latent_dim)
z = z.cuda(current_device)
samples = self.decode(z)
return samples
def generate(self, x: Tensor, **kwargs) -> Tensor:
"""
Given an input image x, returns the reconstructed image
:param x: (Tensor) [B x C x H x W]
:return: (Tensor) [B x C x H x W]
"""
return self.forward(x)[0]
class MSSIM(nn.Module):
def __init__(self,
in_channels: int = 3,
window_size: int=11,
size_average:bool = True) -> None:
"""
Computes the differentiable MS-SSIM loss
Reference:
[1] https://github.com/jorge-pessoa/pytorch-msssim/blob/dev/pytorch_msssim/__init__.py
(MIT License)
:param in_channels: (Int)
:param window_size: (Int)
:param size_average: (Bool)
"""
super(MSSIM, self).__init__()
self.in_channels = in_channels
self.window_size = window_size
self.size_average = size_average
def gaussian_window(self, window_size:int, sigma: float) -> Tensor:
kernel = torch.tensor([exp((x - window_size // 2)**2/(2 * sigma ** 2))
for x in range(window_size)])
return kernel/kernel.sum()
def create_window(self, window_size, in_channels):
_1D_window = self.gaussian_window(window_size, 1.5).unsqueeze(1)
_2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
window = _2D_window.expand(in_channels, 1, window_size, window_size).contiguous()
return window
def ssim(self,
img1: Tensor,
img2: Tensor,
window_size: int,
in_channel: int,
size_average: bool) -> Tensor:
device = img1.device
window = self.create_window(window_size, in_channel).to(device)
mu1 = F.conv2d(img1, window, padding= window_size//2, groups=in_channel)
mu2 = F.conv2d(img2, window, padding= window_size//2, groups=in_channel)
mu1_sq = mu1.pow(2)
mu2_sq = mu2.pow(2)
mu1_mu2 = mu1 * mu2
sigma1_sq = F.conv2d(img1 * img1, window, padding = window_size//2, groups=in_channel) - mu1_sq
sigma2_sq = F.conv2d(img2 * img2, window, padding = window_size//2, groups=in_channel) - mu2_sq
sjx_alo
- 粉丝: 1w+
- 资源: 1235
最新资源
- YOLOv5 PyTorch 格式注释番茄叶病检测数据集下载
- C#ASP.NET手机微信附近预约洗车小程序平台源码(前台+后台)数据库 SQL2008源码类型 WebForm
- 11140资源描述资源标签*所属分类01
- 11140资源描述资源标签*所属分类
- 基于Matlab的室内结构化建模代码
- 下载视频工具,c++开发
- PHP的ThinkPHP5多小区物业管理系统源码(支持多小区)数据库 MySQL源码类型 WebForm
- 【安卓毕业设计】Android作业源码(完整前后端+mysql+说明文档).zip
- 【安卓毕业设计】基于Android租房软件app源码(完整前后端+mysql+说明文档).zip
- Untitled7.ipynb
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈