Feedforward_neural_network
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)
cuda
input_size = 28 * 28
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001
train_dataset = torchvision.datasets.MNIST(root='../../data/',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST('../../data/',
train=False,
transform=transforms.ToTensor())
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=True)
class NeuralNet(nn.Module):
def __init__(self, input_size, hidden_size, num_classes):
super(NeuralNet, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_size, num_classes)
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.fc2(out)
return out
model = NeuralNet(input_size, hidden_size,num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.reshape(-1, input_size).to(device)
labels = labels.to(device)
outputs = model(images)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print('Epoch [{}/{}], Step [{}/{}], loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
Epoch [1/5], Step [100/600], loss: 0.2747
Epoch [1/5], Step [200/600], loss: 0.2937
Epoch [1/5], Step [300/600], loss: 0.3607
Epoch [1/5], Step [400/600], loss: 0.2670
Epoch [1/5], Step [500/600], loss: 0.2306
Epoch [1/5], Step [600/600], loss: 0.1151
Epoch [2/5], Step [100/600], loss: 0.0780
Epoch [2/5], Step [200/600], loss: 0.1091
Epoch [2/5], Step [300/600], loss: 0.1936
Epoch [2/5], Step [400/600], loss: 0.1072
Epoch [2/5], Step [500/600], loss: 0.0502
Epoch [2/5], Step [600/600], loss: 0.0394
Epoch [3/5], Step [100/600], loss: 0.1356
Epoch [3/5], Step [200/600], loss: 0.0447
Epoch [3/5], Step [300/600], loss: 0.0266
Epoch [3/5], Step [400/600], loss: 0.0744
Epoch [3/5], Step [500/600], loss: 0.1216
Epoch [3/5], Step [600/600], loss: 0.0685
Epoch [4/5], Step [100/600], loss: 0.0739
Epoch [4/5], Step [200/600], loss: 0.0348
Epoch [4/5], Step [300/600], loss: 0.0894
Epoch [4/5], Step [400/600], loss: 0.0911
Epoch [4/5], Step [500/600], loss: 0.0651
Epoch [4/5], Step [600/600], loss: 0.0704
Epoch [5/5], Step [100/600], loss: 0.0388
Epoch [5/5], Step [200/600], loss: 0.0231
Epoch [5/5], Step [300/600], loss: 0.0143
Epoch [5/5], Step [400/600], loss: 0.1222
Epoch [5/5], Step [500/600], loss: 0.0317
Epoch [5/5], Step [600/600], loss: 0.1114
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.reshape(-1, input_size).to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))
Accuracy of the network on the 10000 test images: 97.86 %
torch.save(model.state_dict(), 'model_param.ckpt')
model = model.load_state_dict(torch.load('model_param.ckpt'))