def evaluation(args, model, data_loader, metric):
model.eval()
metric.reset()
for batch in data_loader:
input_ids, segment_ids, labels = batch
logits = model(input_ids, segment_ids)
if args.task_name in ['atis_intent', 'mrda', 'swda']:
correct = metric.compute(logits, labels)
metric.update(correct)
else:
metric.update(logits, labels)
model.train()
metric_out = metric.accumulate()
print('Total samples: %d' % (len(data_loader) * args.test_batch_size))
if args.task_name == 'udc':
print('R1@10: %.4f - R2@10: %.4f - R5@10: %.4f\n' %
(metric_out[0], metric_out[1], metric_out[2]))
return metric_out[0]
elif args.task_name == 'dstc2':
print('Joint_acc: %.4f\n' % metric_out)
return metric_out
elif args.task_name == 'atis_slot':
print('F1_micro: %.4f\n' % metric_out)
return metric_out
elif args.task_name in ['atis_intent', 'mrda', 'swda']:
print('Acc: %.4f\n' % metric_out)
return metric_out
def print_logs(args, step, logits, labels, loss, total_time, metric):
if args.task_name in ['udc', 'atis_intent', 'mrda', 'swda']:
if args.task_name == 'udc':
metric = Accuracy()
metric.reset()
correct = metric.compute(logits, labels)
metric.update(correct)
acc = metric.accumulate()
print('step %d - loss: %.4f - acc: %.4f - %.3fs/step' %
(step, loss, acc, total_time / args.logging_steps))
elif args.task_name == 'dstc2':
metric.reset()
metric.update(logits, labels)
joint_acc = metric.accumulate()
print('step %d - loss: %.4f - joint_acc: %.4f - %.3fs/step' %
(step, loss, joint_acc, total_time / args.logging_steps))
elif args.task_name == 'atis_slot':
metric.reset()
metric.update(logits, labels)
f1_micro = metric.accumulate()
print('step %d - loss: %.4f - f1_micro: %.4f - %.3fs/step' %
(step, loss, f1_micro, total_time / args.logging_steps))