AutoEncoder（自编码：以Mnist数据集为例）

￡神魔★判官ぃ 2021-12-12 04:43 481阅读 0赞

本例以pytorch框架进行实验：

#coding = utf-8
    import torch
    import torch.nn as nn
    import torch.utils.data as Data
    import torchvision
    import torch.optim as optim
    import matplotlib.pyplot as plt
    from mpl_toolkits.mplot3d import Axes3D
    from matplotlib import cm
    import numpy as np
    from torch.autograd import Variable
    
    # torch.manual_seed(1)    # reproducible
    
    # Hyper Parameters
    EPOCH = 5
    BATCH_SIZE = 64
    LR = 0.001         # learning rate
    DOWNLOAD_MNIST = True
    N_TEST_IMG = 5
    
    # Mnist digits dataset
    train_data = torchvision.datasets.MNIST(
        root='./mnist_data/',
        train=True,                                     # this is training data
        transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                        # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
        download=DOWNLOAD_MNIST,                        # download it if you don't have it
    )
    
    # plot one example
    # print(train_data.train_data.size())     # (60000, 28, 28)
    # print(train_data.train_labels.size())   # (60000)
    # plt.imshow(train_data.train_data[2].numpy(), cmap='gray')
    # plt.title('%i' % train_data.train_labels[2])
    # plt.show()
    
    # Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
    train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
    
    
    class AutoEncoder(nn.Module):
        def __init__(self):
            super(AutoEncoder, self).__init__()
            self.encoder = nn.Sequential(
                nn.Linear(28*28,128),
                nn.Tanh(),
                nn.Linear(128,64),
                nn.Tanh(),
                nn.Linear(64, 12),
                nn.Tanh(),
                nn.Linear(12, 3),
    
            )
            self.decoder = nn.Sequential(
                nn.Linear(3, 12),
                nn.Tanh(),
                nn.Linear(12, 64),
                nn.Tanh(),
                nn.Linear(64, 128),
                nn.Tanh(),
                nn.Linear(128, 28*28),
                nn.Sigmoid(),
            )
        def forward(self, x):
            encoded = self.encoder(x)
            decoded = self.decoder(encoded)
            return decoded
    
    en = AutoEncoder()
    print(en)
    
    optimizer = optim.Adam(en.parameters(),lr=LR)
    loss_func = nn.MSELoss()
    
    # initialize figure
    plt.figure()
    f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
    plt.ion()   # continuously plot
    
    # original data (first row) for viewing
    view_data = train_data.data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.
    for i in range(N_TEST_IMG):
        a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())
    
    
    for epoch in range(EPOCH):
        for step,(x,y) in enumerate(train_loader):
            b_x = Variable(x.view(-1,28*28))
            b_y = Variable(x.view(-1,28*28))
            b_label = Variable(y)
    
            decoded = en(b_x)
    
            loss = loss_func(decoded,b_y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
    
            if step % 100 ==0:
                print('Epoch:',epoch,'|train loss:%.4f'%loss.item())
    
                # plotting decoded image (second row)
                decoded_data = en(view_data)
                for i in range(N_TEST_IMG):
                    a[1][i].clear()
                    a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
                    a[1][i].set_xticks(())
                    a[1][i].set_yticks(())
                plt.draw()
                plt.pause(0.05)
    
    plt.ioff()
    plt.show()
    
    # visualize in 3D plot
    view_data = train_data.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.
    encoded_data= en(view_data)
    fig = plt.figure(2); ax = Axes3D(fig)
    X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
    values = train_data.targets[:200].numpy()
    for x, y, z, s in zip(X, Y, Z, values):
        c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)
    ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())
    plt.show()