MCPcopy Create free account
hub / github.com/google-research/language / model_function

Function model_function

language/boolq/run_recurrent_model_boolq.py:434–470  ·  view source on GitHub ↗

Builds the `tf.estimator.EstimatorSpec` to train/eval with.

(features, labels, mode, params)

Source from the content-addressed store, hash-verified

432 # Need a named parameter `param` since this will be called
433 # with named arguments, so pylint: disable=unused-argument
434 def model_function(features, labels, mode, params):
435 """Builds the `tf.estimator.EstimatorSpec` to train/eval with."""
436 is_train = mode == tf_estimator.ModeKeys.TRAIN
437 logits = predict(is_train, embeddings, features["premise"],
438 features["hypothesis"])
439
440 loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
441 labels=tf.to_int32(labels), logits=logits)
442 loss = tf.reduce_mean(loss)
443 if mode == tf_estimator.ModeKeys.TRAIN:
444 train_op = get_train_op(loss)
445 else:
446 # Don't build the train_op unnecessarily, since the ADAM variables can
447 # cause problems with loading checkpoints on CPUs.
448 train_op = None
449 metrics = dict(
450 accuracy=tf.metrics.accuracy(
451 tf.argmax(logits, 1, output_type=tf.int32), tf.to_int32(labels)))
452
453 checkpoint_file = FLAGS.checkpoint_file
454 if checkpoint_file is None:
455 scaffold = None
456 else:
457 saver = tf.train.Saver(tf.trainable_variables())
458
459 def _init_fn(_, sess):
460 saver.restore(sess, checkpoint_file)
461
462 scaffold = tf.train.Scaffold(init_fn=_init_fn)
463
464 return tf_estimator.EstimatorSpec(
465 mode=mode,
466 scaffold=scaffold,
467 loss=loss,
468 predictions=None,
469 train_op=train_op,
470 eval_metric_ops=metrics)
471
472 def compare_fn(best_eval_result, current_eval_result):
473 return best_eval_result["accuracy"] < current_eval_result["accuracy"]

Callers

nothing calls this directly

Calls 2

predictFunction · 0.85
get_train_opFunction · 0.85

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…