x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2(x), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.log_softmax(x)
model = Net()
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=H.lr, momentum=H.momentum)
train(
model, optimizer, tn_loader, val_loader, H, S, inner_log,
struct(val_acc=acc_metric(model, val_loader),
val_loss=nll_metric(model, val_loader),
tn_loss=nll_metric(model, tn_loader),
tn_acc=acc_metric(model, tn_loader)))
val_accs = [
batch.val_acc for batch in inner_log.metrics() if 'val_acc' in batch
]
val_losses = [
batch.val_loss for batch in inner_log.metrics() if 'val_loss' in batch
]
tn_accs = [
batch.tn_acc for batch in inner_log.metrics() if 'tn_acc' in batch
]
tn_losses = [
batch.tn_loss for batch in inner_log.metrics() if 'tn_loss' in batch
]
def __init__(self):
super(Net, self).__init__()
self.features = vgg('vgg11')
self.classifier = nn.Linear(512, 10)
def forward(self, x):
out = self.features(x)
out = out.view(out.size(0), -1)
out = self.classifier(out)
out = F.log_softmax(out)
return out
model = Net()
# model = Net()
model.cuda()
optimizer = optim.SGD(model.parameters(), lr=H.lr, momentum=H.momentum)
print('Beginning training')
train(model,
optimizer,
tn_loader,
val_loader,
H,
S,
log,
struct(val_acc=acc_metric(model, val_loader),
val_loss=nll_metric(model, val_loader)),
param_log_freq=3)