pytorchのoptimizerとscheduler

optimizerはtrainのdatasetごと

dataloaderの中のdataset

code:py

for input, target in dataset:

optimizer.zero_grad()

output = model(input)

loss = loss_fn(output, target)

loss.backward()

optimizer.step()

schedulerはepochごと

zero_gradも忘れてるし