def vector_loss(self, targets, predictions, logits):
with tf.variable_scope('loss_{}'.format(self.name)):
if self.loss['type'] == MEAN_SQUARED_ERROR:
train_loss = tf.reduce_sum(get_squared_error(
targets, predictions, self.name),
axis=1)
elif self.loss['type'] == MEAN_ABSOLUTE_ERROR:
train_loss = tf.reduce_sum(get_absolute_error(
targets, predictions, self.name),
axis=1)
elif self.loss['type'] == SOFTMAX_CROSS_ENTROPY:
train_loss = weighted_softmax_cross_entropy(
logits, targets, self.loss)
else:
train_mean_loss = None
train_loss = None
raise ValueError('Unsupported loss type {}'.format(
self.loss['type']))
train_mean_loss = tf.reduce_mean(train_loss,
name='train_mean_loss_{}'.format(
self.name))
return train_mean_loss, train_loss
def _get_measures(self, targets, predictions):
with tf.variable_scope('measures_{}'.format(self.name)):
error_val = get_error(targets, predictions, self.name)
absolute_error_val = get_absolute_error(targets, predictions,
self.name)
squared_error_val = get_squared_error(targets, predictions,
self.name)
r2_val = get_r2(targets, predictions, self.name)
return error_val, squared_error_val, absolute_error_val, r2_val
def _get_measures(self, targets, predictions):
with tf.variable_scope('measures_{}'.format(self.name)):
error_val = get_error(targets, predictions, self.name)
absolute_error_val = tf.reduce_sum(get_absolute_error(
targets, predictions, self.name),
axis=1)
squared_error_val = tf.reduce_sum(get_squared_error(
targets, predictions, self.name),
axis=1)
# TODO - not sure if this is correct
r2_val = tf.reduce_sum(get_r2(targets, predictions, self.name))
return error_val, squared_error_val, absolute_error_val, r2_val
