View more, visit my tutorial page: https://morvanzhou.github.io/tutorials/ My Youtube Channel: https://www.youtube.com/user/MorvanZhou Dependencies:
import torch
import torch.nn as nn
from torch.autograd import Variable
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
%matplotlib inline
torch.manual_seed(1) # reproducible
<torch._C.Generator at 0x7f54e0186918>
# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005 # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5
# 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=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()
torch.Size([60000, 28, 28]) torch.Size([60000])
# 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), # compress to 3 features which can be visualized in plt
)
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(), # compress to a range (0, 1)
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
autoencoder = AutoEncoder()
print(autoencoder)
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
# original data (first row) for viewing
view_data = Variable(train_data.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.)
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader):
b_x = Variable(x.view(-1, 28*28)) # batch x, shape (batch, 28*28)
b_y = Variable(x.view(-1, 28*28)) # batch y, shape (batch, 28*28)
b_label = Variable(y) # batch label
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 % 500 == 0 and epoch in [0, 5, EPOCH-1]:
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data[0])
# plotting decoded image (second row)
_, decoded_data = autoencoder(view_data)
# initialize figure
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
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 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.show(); plt.pause(0.05)
AutoEncoder ( (encoder): Sequential ( (0): Linear (784 -> 128) (1): Tanh () (2): Linear (128 -> 64) (3): Tanh () (4): Linear (64 -> 12) (5): Tanh () (6): Linear (12 -> 3) ) (decoder): Sequential ( (0): Linear (3 -> 12) (1): Tanh () (2): Linear (12 -> 64) (3): Tanh () (4): Linear (64 -> 128) (5): Tanh () (6): Linear (128 -> 784) (7): Sigmoid () ) ) Epoch: 0 | train loss: 0.2323
Epoch: 0 | train loss: 0.0559
Epoch: 5 | train loss: 0.0374
Epoch: 5 | train loss: 0.0349
Epoch: 9 | train loss: 0.0367
Epoch: 9 | train loss: 0.0351
# visualize in 3D plot
view_data = Variable(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)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
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)); 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()