pytorch 卷积自编码器

import torch
import torchvision
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.utils import save_image
from torchvision.datasets import MNIST
import os
batch_size = 128

img_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5), (0.5))
])
data_path="/DATA1/zhangjingxiao/yxk/dataset/"
dataset = MNIST(data_path, transform=img_transform)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
print(dataset)
print("=================")
print(dataset.data.shape)

结果如下
实现卷积自编码器

import torch

__author__ = 'SherlockLiao'

import torch
import torchvision
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.utils import save_image
from torchvision.datasets import MNIST
import os

if not os.path.exists('./dc_img'):
    os.mkdir('./dc_img')


def to_img(x):
    x = 0.5 * (x + 1)
    x = x.clamp(0, 1)
    x = x.view(x.size(0), 1, 28, 28)
    return x


num_epochs = 100
batch_size = 128
learning_rate = 1e-3

img_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5), (0.5))
])
data_path="/DATA1/zhangjingxiao/yxk/dataset/"
dataset = MNIST(data_path, transform=img_transform)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

class autoencoder(nn.Module):
    def __init__(self):
        super(autoencoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Conv2d(1, 16, 3, stride=3, padding=1),  # b, 16, 10, 10
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=2),  # b, 16, 5, 5
            nn.Conv2d(16, 8, 3, stride=2, padding=1),  # b, 8, 3, 3
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=1)  # b, 8, 2, 2
        )
        self.decoder = nn.Sequential(
            nn.ConvTranspose2d(8, 16, 3, stride=2),  # b, 16, 5, 5
            nn.ReLU(True),
            nn.ConvTranspose2d(16, 8, 5, stride=3, padding=1),  # b, 8, 15, 15
            nn.ReLU(True),
            nn.ConvTranspose2d(8, 1, 2, stride=2, padding=1),  # b, 1, 28, 28
            nn.Tanh()
        )

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x


model = autoencoder().cuda()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate,
                             weight_decay=1e-5)

for epoch in range(num_epochs):
    total_loss = 0
    for data in dataloader:
        img, _ = data
        img = Variable(img).cuda()
        # ===================forward=====================
        output = model(img)
        loss = criterion(output, img)
        # ===================backward====================
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_loss += loss.data
    # ===================log========================
    print('epoch [{}/{}], loss:{:.4f}'
          .format(epoch+1, num_epochs, total_loss))
    if epoch % 10 == 0:
        pic = to_img(output.cpu().data)
        save_image(pic, './dc_img/image_{}.png'.format(epoch))

torch.save(model.state_dict(), './conv_autoencoder.pth')

最终的结果如下