import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Hyper-parameters
num_classes = 10
num_epochs = 2
batch_size = 100
learning_rate = 0.001
# NOTE: an image is composed of 28x28 pixels.
input_size = 28
sequence_length = 28
hidden_size = 128
num_layers = 2
# ------------------------------------------------------------------------
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(RNN, self).__init__()
self.num_layers = num_layers
self.hidden_size = hidden_size
self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
out, _ = self.rnn(x, h0)
out = out[:, -1, :]
out = self.fc(out)
return out
# ------------------------------------------------------------------------
class GRU(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(GRU, self).__init__()
self.num_layers = num_layers
self.hidden_size = hidden_size
self.gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0),
self.hidden_size).to(device)
out, _ = self.gru(x, h0)
out = out[:, -1, :]
out = self.fc(out)
return out
# ------------------------------------------------------------------------
class LSTM(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(LSTM, self).__init__()
self.num_layers = num_layers
self.hidden_size = hidden_size
self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, x):
h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
out, _ = self.lstm(x, (h0,c0))
out = out[:, -1, :]
out = self.fc(out)
return out
# ------------------------------------------------------------------------
# model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
model = GRU(input_size, hidden_size, num_layers, num_classes).to(device)
# model = LSTM(input_size, hidden_size, num_layers, num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# ------------------------------------------------------------------------
# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='./data',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST(root='./data',
train=False,
transform=transforms.ToTensor())
# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# ------------------------------------------------------------------------
# Train the model
n_total_steps = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
# origin shape: [N, 1, 28, 28]
# resized: [N, 28, 28]
images = images.reshape(-1, sequence_length, input_size).to(device)
labels = labels.to(device)
# Forward pass
outputs = model(images)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print (f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{n_total_steps}], Loss: {loss.item():.4f}')
# ------------------------------------------------------------------------
# Test the model
# In test phase, we don't need to compute gradients (for memory efficiency)
with torch.no_grad():
n_correct = 0
n_samples = 0
for images, labels in test_loader:
images = images.reshape(-1, sequence_length, input_size).to(device)
labels = labels.to(device)
outputs = model(images)
# max returns (value ,index)
_, predicted = torch.max(outputs.data, 1)
n_samples += labels.size(0)
n_correct += (predicted == labels).sum().item()
acc = 100.0 * n_correct / n_samples
print(f'Accuracy of the network on the 10000 test images: {acc} %')