def test_log_loss_from_logits(self):
"""Test computing cross-entropy loss from logits."""
logits = np.array([[1, 2, 0, -1], [1, 2, 0, -1], [-1, 3, 0, 0]])
labels = np.array([0, 3, 1])
expected_loss = np.array([1.4401897, 3.4401897, 0.11144278])
loss = utils.log_loss_from_logits(labels, logits)
np.testing.assert_allclose(expected_loss, loss, atol=1e-7)
def get_loss_test(self):
"""Calculates (if needed) cross-entropy losses for the test set."""
if self.loss_test is None:
if self.logits_train is not None:
self.loss_test = utils.log_loss_from_logits(self.labels_test,
self.logits_test)
else:
self.loss_test = utils.log_loss(self.labels_test, self.probs_test)
return self.loss_test
def get_loss_test(self):
"""Calculates (if needed) cross-entropy losses for the test set.
Returns:
Loss (or None if neither the loss nor the labels are present).
"""
if self.loss_test is None:
if self.labels_test is None:
return None
if self.logits_test is not None:
self.loss_test = utils.log_loss_from_logits(
self.labels_test, self.logits_test)
else:
self.loss_test = utils.log_loss(self.labels_test,
self.probs_test)
return self.loss_test
def get_loss_train(self):
"""Calculates (if needed) cross-entropy losses for the training set."""
if self.loss_train is None:
self.loss_train = utils.log_loss_from_logits(
self.labels_train, self.logits_train)
return self.loss_train
