【pytorch】Deepfake(深度换脸)-基于自编码器的Pytorch&keras完整代码实现

最新推荐文章于 2024-06-08 09:35:26 发布

yipala

最新推荐文章于 2024-06-08 09:35:26 发布

阅读量2k

点赞数

分类专栏： pytorch 自编密码器卷积神经网络文章标签： pycharm AE

本文链接：https://blog.csdn.net/yipala/article/details/102615755

版权

Pytorch

import torch
import torch.utils.data
from torch import nn, optim
from padding_same_conv import Conv2d


def toTensor(img):
    img = torch.from_numpy(img.transpose((0, 3, 1, 2)))
    return img


def var_to_np(img_var):
    return img_var.data.cpu().numpy()


class _ConvLayer(nn.Sequential):
    def __init__(self, input_features, output_features):
        super(_ConvLayer, self).__init__()
        self.add_module('conv2', Conv2d(input_features, output_features,
                                        kernel_size=5, stride=2))
        self.add_module('leakyrelu', nn.LeakyReLU(0.1, inplace=True))


class _UpScale(nn.Sequential):
    def __init__(self, input_features, output_features):
        super(_UpScale, self).__init__()
        self.add_module('conv2_', Conv2d(input_features, output_features * 4,
                                         kernel_size=3))
        self.add_module('leakyrelu', nn.LeakyReLU(0.1, inplace=True))
        self.add_module('pixelshuffler', _PixelShuffler())


class Flatten(nn.Module):

    def forward(self, input):
        output = input.view(input.size(0), -1)
        return output


class Reshape(nn.Module