import matplotlib.pyplot as plt
from tqdm import tqdm
import torch
from torch.utils.data import DataLoader
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision.transforms as transforms
from torchvision.datasets import MNIST
from torchsummary import summary
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# in-size out-size
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.dropout = nn.Dropout2d(0.5)
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
# CNN
x = self.conv1(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
x = self.conv2(x)
x = self.dropout(x)
x = F.max_pool2d(x, 2)
x = F.relu(x)
# (? x ?) => (320 x ?)
x = x.view(-1, 320)
x = self.fc1(x)
x = F.relu(x)
x = self.dropout(x)
x = self.fc2(x)
output = F.log_softmax(x, dim=1)
return output
def data():
# Train Data
train_data_with_label = MNIST(
'data/', train=True, download=True, transform=transforms.ToTensor())
train_loader = DataLoader(train_data_with_label, batch_size=4, shuffle=True)
# Test Data
test_data_with_label = MNIST(
'data/', train=False, download=True, transform=transforms.ToTensor())
test_loader = DataLoader(
test_data_with_label, batch_size=4, shuffle=False)
return train_loader, test_loader
def train(model, device, train_loader, optimizer, epoch):
model.train()
criterion = nn.CrossEntropyLoss()
with tqdm(total=len(train_loader.dataset)) as progress:
for batch_idx, (data, target) in tqdm(enumerate(train_loader)):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
# ソフトマックスロスエントロピー
loss = criterion(output, target)
loss.backward()
optimizer.step()
progress.update(len(data))
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)))
def main(epochs=1):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)
model = Net().to(device)
summary(model, (1, 28, 28))
# SGD
optimizer = optim.SGD(model.parameters(), lr=0.01)
train_loader, test_loader = data()
for epoch in range(1, epochs + 1):
train(model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
if __name__ == '__main__':
main()