criterion = nn.CrossEntropyLoss()
normal_arc = best_reward_arc[0]
reduction_arc = best_reward_arc[1]
child = Child().to(device)
child_optimizer = optim.SGD(child.parameters(),
lr=0.05,
momentum=0.9,
weight_decay=1e-4,
nesterov=True)
cosine_lr_scheduler = cosine_annealing_scheduler(child_optimizer, lr=0.05)
best_acc = 0
for epoch in range(300):
child.train()
cosine_lr_scheduler.step()
train_loss = 0
correct = 0
total = 0
for batch_idx, (inputs, targets) in enumerate(train_loader):
inputs = inputs.to(device)
targets = targets.to(device)
outputs, aux_outs = child(inputs, normal_arc, reduction_arc)
loss = criterion(outputs, targets)
if args.use_auxiliary:
loss += 0.4 * criterion(aux_outs, targets)
child_optimizer.zero_grad()
loss.backward()
