import torch import torch.nn as nn import torch.utils.data as Data import torchvision import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D from matplotlib import cm import numpy as np import os os.environ['KMP_DUPLICATE_LIB_OK']='TRUE' # torch.manual_seed(1) # reproducible # 超参数 EPOCH = 10 BATCH_SIZE = 64 LR = 0.005 # learning rate DOWNLOAD_MNIST = False # 下过数据的话, 就可以设置成 False N_TEST_IMG = 5 # 下过数据的话, 就可以设置成 False # Mnist digits dataset train_data = torchvision.datasets.MNIST( root='./mnist/', 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=True, # 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): # 压缩 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), # 压缩成3个特征, 进行 3D 图像可视化 ) # 解压 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(), # 激励函数让输出值在 (0, 1) ) def forward(self, x): encoded = self.encoder(x) decoded = self.decoder(encoded) return encoded, decoded autoencoder = AutoEncoder() optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR) loss_func = nn.MSELoss() # initialize figure f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2)) plt.ion() # continuously plot view_data = train_data.train_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, b_label) in enumerate(train_loader): b_x = x.view(-1, 28 * 28) # batch x, shape (batch, 28*28) b_y = x.view(-1, 28 * 28) # batch y, shape (batch, 28*28) encoded, decoded = autoencoder(b_x) loss = loss_func(decoded, b_y) # mean square error optimizer.zero_grad() # clear gradients for this training step loss.backward() # backpropagation, compute gradients optimizer.step() # apply gradients if step % 100 == 0: print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy()) # plotting decoded image (second row) _, decoded_data = autoencoder(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() # 提取压缩的特征值 view_data = train_data.train_data[:200].view(-1, 28 * 28).type(torch.FloatTensor) / 255. encoded_data, _ = autoencoder(view_data) fig = plt.figure(2); ax = Axes3D(fig) # 3D图 # x, y, z 的数据值 X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy() # 标签值 values = train_data.train_labels[:200].numpy() for x, y, z, s in zip(X, Y, Z, values): c = cm.rainbow(int(255 * s / 9)); # 上色 ax.text(x, y, z, s, backgroundcolor=c) # 标位子 ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max()) plt.show()
人工智能概论第六次作业
该代码示例展示了如何使用PyTorch构建一个自动编码器模型来处理MNIST手写数字数据集。模型将28x28的图像压缩到3个特征维度,然后解压缩回原始大小,以实现数据的降维和重构。通过在训练过程中计算均方误差损失,不断调整网络权重。最后,通过3D可视化展示了编码后的特征分布。
摘要由CSDN通过智能技术生成