False)] = TaskSpecificARCDataset.WordMap['pad_symbol']
outputs = train_forward(net, inputs, inputs_mask, task, task_mask)
# print(inputs.shape, outputs.shape, targets.shape, answers.shape)
loss = compute_balance_loss(
outputs, targets, answers,
TaskSpecificARCDataset.WordMap['pad_symbol'])
_, output_index = torch.max(outputs, dim=-1)
output_index = output_index.to(outputs.dtype)
element_accuracy = compute_element_accuracy(
output_index, targets,
TaskSpecificARCDataset.WordMap['pad_symbol'])
mask_accuracy = compute_mask_accuracy(
inp, output_index, targets,
TaskSpecificARCDataset.WordMap['pad_symbol'])
correct_accuracy = compute_corrects_accuracy(
output_index, targets,
TaskSpecificARCDataset.WordMap['pad_symbol'])
loss.backward()
optimizer.step()
optimizer.zero_grad()
loging(writer,
'train',
epoch,
step,
time.time() - start_time,
dataset_size=len(dataset),
batch_size=len(inputs),
**{
inputs.ne(padding).to(torch.float), ctx_input,
ctx_input.ne(padding).to(torch.float), ctx_targets,
ctx_targets.ne(padding).to(torch.float))
loss = compute_balance_loss(outputs, targets, answers,
padding) + compute_task_loss(
predict_task, task[:, 0, 0], padding)
_, predict_task = torch.max(predict_task, dim=-1)
_, output_index = torch.max(outputs, dim=-1)
output_index = output_index.to(outputs.dtype)
task_accuracy = compute_task_accuracy(predict_task, task[:, 0, 0],
padding)
element_accuracy = compute_element_accuracy(output_index, targets,
padding)
mask_accuracy = compute_mask_accuracy(inputs, output_index, targets,
padding)
correct_accuracy = compute_corrects_accuracy(output_index, targets,
padding)
loss.backward()
optimizer.step()
optimizer.zero_grad()
loging(writer,
'train',
epoch,
step,
time.time() - start_time,
dataset_size=len(dataset),
batch_size=len(inputs),
**{
'loss': loss,
'element_accuracy': element_accuracy,