def validate(self):
self.model.eval()
val_total_loss = 0.0
mes = "Epoch {}, validation average loss:{:.4f}, Perplexity:{:.4f}"
with torch.no_grad():
for imgs, tgt4training, tgt4cal_loss in self.val_loader:
imgs = imgs.to(self.device)
tgt4training = tgt4training.to(self.device)
tgt4cal_loss = tgt4cal_loss.to(self.device)
epsilon = cal_epsilon(self.args.decay_k, self.total_step,
self.args.sample_method)
logits = self.model(imgs, tgt4training, epsilon)
loss = cal_loss(logits, tgt4cal_loss)
val_total_loss += loss
try:
avg_loss = val_total_loss / len(self.val_loader)
except:
avg_loss = val_total_loss
print(mes.format(self.epoch, avg_loss, 2**avg_loss))
wandb.log({
"epoch": self.epoch,
"val avrg loss": avg_loss,
"perplexit": 2**avg_loss
})
if avg_loss < self.best_val_loss:
self.best_val_loss = avg_loss
self.save_model('best_ckpt')
return avg_loss
def train_step(self, imgs, tgt4training, tgt4cal_loss):
self.optimizer.zero_grad()
imgs = imgs.to(self.device)
tgt4training = tgt4training.to(self.device)
tgt4cal_loss = tgt4cal_loss.to(self.device)
epsilon = cal_epsilon(self.args.decay_k, self.total_step,
self.args.sample_method)
logits = self.model(imgs, tgt4training, epsilon)
# calculate loss
loss = cal_loss(logits, tgt4cal_loss)
self.step += 1
self.total_step += 1
loss.backward()
clip_grad_norm_(self.model.parameters(), self.args.clip)
self.optimizer.step()
return loss.item()