0221225/Pytorch-MLP
/mnist.py
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.utils.data import DataLoader
from torch.autograd import Variable
train = datasets.MNIST(
root="data",
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
]),
)
test = datasets.MNIST(
root="data",
train=False,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
]),
)
train_loader = DataLoader(train, batch_size=64)
test_loader = DataLoader(test, batch_size=1000)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28 * 28, 128)
self.fc2 = nn.Linear(128, 64)
self.fc3 = nn.Linear(64, 10)
def forward(self, x):
x = x.view(-1, 28 * 28)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.log_softmax(self.fc3(x), dim=1)
return x
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss().to(device)
for epoch in range(5):
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print(f'Epoch: {epoch}, Batch: {batch_idx}, Loss: {loss.item()}')
# test
model.eval()
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
pred = output.argmax(dim=1)
correct += pred.eq(target).sum().item()
print(f'Test Accuracy: {100. * correct / len(test_loader.dataset):.2f} %')
/README.md
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.utils.data import DataLoader
from torch.autograd import Variable
train = datasets.MNIST(
root="data",
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
]),
)
test = datasets.MNIST(
root="data",
train=False,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
]),
)
train_loader = DataLoader(train, batch_size=64)
test_loader = DataLoader(test, batch_size=1000)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28 * 28, 128)
self.fc2 = nn.Linear(128, 64)
self.fc3 = nn.Linear(64, 10)
def forward(self, x):
x = x.view(-1, 28 * 28)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.log_softmax(self.fc3(x), dim=1)
return x
model = Net()
optimizer = optim.SGD(model.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss().to(device)
def train(model, device, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
output = model(data)
loss = criterion(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print(f'Epoch: {epoch}, Batch: {batch_idx}, Loss: {loss.item()}')
def test(model, device, test_loader):
model.eval()
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
pred = output.argmax(dim=1)
correct += pred.eq(target).sum().item()
print(f'Test Accuracy: {100. * correct / len(test_loader.dataset):.2f} %')
for epoch in range(5):
train(model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
/convnet.py
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.utils.data import DataLoader
from torch.autograd import Variable
train = datasets.MNIST(
root="data",
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
]),
)
test = datasets.MNIST(
root="data",
train=False,
download=True,
transform=transforms