def train(engine, mini_batch):
# You have to reset the gradients of all model parameters
# before to take another step in gradient descent.
engine.model.train() # Because we assign model as class variable, we can easily access to it.
engine.optimizer.zero_grad()
x, y = mini_batch.text, mini_batch.label
x, y = x.to(engine.device), y.to(engine.device)
# Take feed-forward
y_hat = engine.model(x)
loss = engine.crit(y_hat, y)
loss.backward()
# Calculate accuracy only if 'y' is LongTensor,
# which means that 'y' is one-hot representation.
if isinstance(y, torch.LongTensor) or isinstance(y, torch.cuda.LongTensor):
accuracy = (torch.argmax(y_hat, dim=-1) == y).sum() / float(y.size(0))
else:
accuracy = 0
p_norm = float(get_parameter_norm(engine.model.parameters()))
g_norm = float(get_grad_norm(engine.model.parameters()))
# Take a step of gradient descent.
engine.optimizer.step()
return {
'loss': float(loss),
'accuracy': float(accuracy),
'|param|': p_norm,
'|g_param|': g_norm,
}
def train(engine, mini_batch):
# You have to reset the gradients of all model parameters
# before to take another step in gradient descent.
engine.model.train(
) # Because we assign model as class variable, we can easily access to it.
engine.optimizer.zero_grad()
# text2도 필요 수정필요!
x, x2, y = mini_batch.text1, mini_batch.text2, mini_batch.label
x, x2, y = x.to(engine.device), x2.to(engine.device), y.to(
engine.device)
x = x[:, :engine.config.max_length]
x2 = x2[:, :engine.config.max_length]
x = pad_to_maxseq_to_batch(x, engine.config.max_length, engine.device)
x2 = pad_to_maxseq_to_batch(x2, engine.config.max_length,
engine.device)
#print("엔진", engine.config.max_length)
#print(x2.shape)
# Take feed-forward
y_hat = engine.model(x, x2)
## 19.06.12 추가
#y = y.reshape(9, -1)
#y_hat = torch.argmax(y_hat, dim=-1).to(torch.float)
#print("y_hat", y_hat)
#print("y", y)
loss = engine.crit(y_hat, y)
loss.backward()
# Calculate accuracy only if 'y' is LongTensor,
# which means that 'y' is one-hot representation.
if isinstance(y, torch.LongTensor) or isinstance(
y, torch.cuda.LongTensor):
accuracy = (torch.argmax(y_hat, dim=-1) == y).sum() / float(
y.size(0))
else:
accuracy = 0
p_norm = float(get_parameter_norm(engine.model.parameters()))
g_norm = float(get_grad_norm(engine.model.parameters()))
# Take a step of gradient descent.
engine.optimizer.step()
return {
'loss': float(loss),
'accuracy': float(accuracy),
'|param|': p_norm,
'|g_param|': g_norm,
}
