y_pred = classifier(x_surname=batch_dict["x_surname"])
# step 3. compute the loss
loss = loss_func(y_pred, batch_dict["y_nationality"])
loss_batch = loss.item()
running_loss += (loss_batch - running_loss) / (batch_index + 1)
# step 4. use loss to produce gradients
loss.backward()
# step 5. use optimizer to take gradient step
optimizer.step()
# -------------------------------------------
# compute the accuracy
acc_batch = helper.compute_accuracy(y_pred, batch_dict["y_nationality"])
running_acc += (acc_batch - running_acc) / (batch_index + 1)
# update bar
train_bar.set_postfix(loss=running_loss,
acc=running_acc,
epoch=epoch_index)
train_bar.update()
train_state["train_loss"].append(running_loss)
train_state["train_acc"].append(running_acc)
#
# Iterate over val dataset
#
y_pred = classifier(x_in=batch_dict["x_data"].float())
# step 3. compute the loss
loss = loss_func(y_pred, batch_dict["y_target"].float())
loss_batch = loss.item()
running_loss += (loss_batch - running_loss) / (batch_index + 1)
# step 4. use loss to produce gradients
loss.backward()
# step 5. use optimizer to take gradient step
optimizer.step()
# -------------------------------------------
# compute the accuracy
acc_batch = helper.compute_accuracy(y_pred, batch_dict["y_target"])
running_acc += (acc_batch - running_acc) / (batch_index + 1)
# update bar
train_bar.set_postfix(loss=running_loss,
acc=running_acc,
epoch=epoch_index)
train_bar.update()
train_state["train_loss"].append(running_loss)
train_state["train_acc"].append(running_acc)
#
# Iterate over val dataset
#
y_pred = model(batch_dict["x_source"],
batch_dict["x_source_length"],
output_sequence_size=vectorizer.max_target_length + 1,
sample_probability=sample_probability)
else:
y_pred = model(batch_dict["x_source"],
batch_dict["x_source_length"],
batch_dict["x_target"])
loss = helper.sequence_loss(y_pred, batch_dict["y_target"], mask_index)
loss.backward()
optimizer.step()
running_loss += (loss.item() - running_loss) / (batch_index + 1)
acc_t = helper.compute_accuracy(y_pred, batch_dict["y_target"], mask_index)
running_acc += (acc_t - running_acc) / (batch_index + 1)
train_bar.set_postfix(loss=running_loss,
acc=running_acc,
epoch=epoch_index)
train_bar.update()
train_state["train_loss"].append(running_loss)
train_state["train_acc"].append(running_acc)
dataset.set_split("val")
batch_generator = generate_nmt_batches(dataset,
batch_size=args.batch_size,
device=args.device)
running_loss = 0.0