Classifier for the MNIST dataset using PyTorch¶
This is a "Hello world!" example with PyTorch.
It trains a convolutional neural network on the MNIST dataset.
Credits:
MNIST dataset, see http://yann.lecun.com/exdb/mnist/
Code adapted from the documentation of the PyTorch project
In [1]:
import torch
torch.__version__
Out[1]:
In [2]:
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR
In [3]:
# Define the model, this uses convolutional neural networks
# The model uses convolutional neural network layers
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 32, 3, 1)
self.conv2 = nn.Conv2d(32, 64, 3, 1)
self.dropout1 = nn.Dropout(0.25)
self.dropout2 = nn.Dropout(0.5)
self.fc1 = nn.Linear(9216, 128)
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = self.conv1(x)
x = F.relu(x)
x = self.conv2(x)
x = F.relu(x)
x = F.max_pool2d(x, 2)
x = self.dropout1(x)
x = torch.flatten(x, 1)
x = self.fc1(x)
x = F.relu(x)
x = self.dropout2(x)
x = self.fc2(x)
output = F.log_softmax(x, dim=1)
return output
In [4]:
# The code to run the training step
def train(model, device, train_loader, optimizer, epoch):
log_interval = 100
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
In [5]:
# The code for the evaluating the model using the test dataset
def test(model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
In [6]:
# Code for reading the data, training and evaluating the model on test data
def main():
torch.manual_seed(1)
# Use GPUs for training and testing
device = torch.device("cuda")
# device = torch.device("cpu")
train_kwargs = {'batch_size': 64}
test_kwargs = {'batch_size': 1000}
cuda_kwargs = {'num_workers': 1,
'pin_memory': True,
'shuffle': True}
train_kwargs.update(cuda_kwargs)
test_kwargs.update(cuda_kwargs)
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
dataset1 = datasets.MNIST('../data', train=True, download=True,
transform=transform)
dataset2 = datasets.MNIST('../data', train=False,
transform=transform)
train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs)
test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)
gamma = 0.7
epochs = 5
model = Net().to(device)
optimizer = optim.Adam(model.parameters())
scheduler = StepLR(optimizer, step_size=1, gamma=gamma)
for epoch in range(1, epochs + 1):
train(model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
scheduler.step()
In [7]:
# Run the training and evaluation of the model
main()
In [ ]: