out = self.fc1(x)
out = F.relu(out)
out = self.fc2(out)
return out
#net = Net(input_size, hidden_size, num_classes)
from lenet3 import LeNet
net = LeNet()
net.cuda()
net.train()
# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = PIDOptimizer(net.parameters(),
lr=learning_rate,
weight_decay=0.0001,
momentum=0.9,
I=I,
D=D)
# Train the Model
for epoch in range(num_epochs):
train_loss_log = AverageMeter()
train_acc_log = AverageMeter()
val_loss_log = AverageMeter()
val_acc_log = AverageMeter()
for i, (images, labels) in enumerate(train_loader):
# Convert torch tensor to Variable
images = Variable(images.cuda())
labels = Variable(labels.cuda())
# Forward + Backward + Optimize
def training(optimizer_sign=0):
training_data = {
'train_loss': [],
'val_loss': [],
'train_acc': [],
'val_acc': []
}
net = Net(input_size, hidden_size, num_classes)
# net = Net(input_size, hidden_size, num_classes)
net.cuda()
net.train()
# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
if optimizer_sign == 0:
optimizer = torch.optim.RMSprop(net.parameters(), lr=learning_rate)
elif optimizer_sign == 1:
optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate)
elif optimizer_sign == 2:
optimizer = SGD(net.parameters(),
lr=learning_rate,
weight_decay=0.0001,
momentum=0.9)
elif optimizer_sign == 3:
optimizer = PIDOptimizer(net.parameters(),
lr=learning_rate,
weight_decay=0.0001,
momentum=0.9,
I=I,
D=D)
else:
optimizer = PIDOptimizer(net.parameters(),
lr=learning_rate,
weight_decay=0.0001,
momentum=0.9,
I=I,
D=0)
# Train the Model
for epoch in range(num_epochs):
train_loss_log = AverageMeter()
train_acc_log = AverageMeter()
val_loss_log = AverageMeter()
val_acc_log = AverageMeter()
for i, (images, labels) in enumerate(train_loader):
# Convert torch tensor to Variable
images = images.view(-1, 28 * 28).cuda()
labels = Variable(labels.cuda())
# Forward + Backward + Optimize
optimizer.zero_grad() # zero the gradient buffer
outputs = net(images)
train_loss = criterion(outputs, labels)
train_loss.backward()
optimizer.step()
prec1, prec5 = accuracy(outputs.data, labels.data, topk=(1, 5))
train_loss_log.update(train_loss.data, images.size(0))
train_acc_log.update(prec1, images.size(0))
if (i + 1) % 100 == 0:
print('Epoch [%d/%d], Step [%d/%d], Loss: %.4f, Acc: %.8f' %
(epoch + 1, num_epochs, i + 1, len(train_dataset) //
batch_size, train_loss_log.avg, train_acc_log.avg))
training_data['train_loss'].append(
train_loss_log.avg.detach().cpu().numpy())
training_data['train_acc'].append(
train_acc_log.avg.detach().cpu().numpy())
# Test the Model
net.eval()
correct = 0
loss = 0
total = 0
for images, labels in test_loader:
images = images.view(-1, 28 * 28).cuda()
labels = Variable(labels).cuda()
outputs = net(images)
test_loss = criterion(outputs, labels)
val_loss_log.update(test_loss.data, images.size(0))
prec1, prec5 = accuracy(outputs.data, labels.data, topk=(1, 5))
val_acc_log.update(prec1, images.size(0))
#logger.append([learning_rate, train_loss_log.avg, val_loss_log.avg, train_acc_log.avg, val_acc_log.avg])
print('Accuracy of the network on the 10000 test images: %.8f %%' %
(val_acc_log.avg))
print('Loss of the network on the 10000 test images: %.8f' %
(val_loss_log.avg))
training_data['val_loss'].append(
val_loss_log.avg.detach().cpu().numpy())
training_data['val_acc'].append(val_acc_log.avg.detach().cpu().numpy())
#logger.close()
#logger.plot()
return training_data