Lines Matching refs:math_ops
32 from tensorflow.python.ops import math_ops
212 math_ops.reduce_sum(
213 math_ops.abs(math_ops.cast(weights, dtypes.float64))))
215 return self._options['symmetric_l1_regularization'] * math_ops.add_n(sums)
225 math_ops.reduce_sum(
226 math_ops.square(math_ops.cast(weights, dtypes.float64))))
228 return l2 * math_ops.add_n(sums) / 2.0
242 result_sparse += math_ops.segment_sum(
243 math_ops.multiply(
252 result_dense += math_ops.matmul(dense_features[i],
282 result = math_ops.sigmoid(result)
325 math_ops.cast(
326 array_ops.unique(math_ops.cast(i, dtypes.int32))[0],
419 math_ops.reduce_sum(math_ops.to_double(values), 0))
420 summed_values = math_ops.add_n(shard_sums)
449 predictions = math_ops.cast(
451 labels = math_ops.cast(
454 weights = math_ops.cast(
459 return math_ops.reduce_sum(math_ops.multiply(
462 weights)) / math_ops.reduce_sum(weights)
468 adjusted_labels = math_ops.subtract(2 * labels, all_ones)
472 math_ops.subtract(all_ones,
473 math_ops.multiply(adjusted_labels, predictions)))
474 weighted_error = math_ops.multiply(error, weights)
475 return math_ops.reduce_sum(weighted_error) / math_ops.reduce_sum(
479 err = math_ops.subtract(labels, predictions)
481 weighted_squared_err = math_ops.multiply(math_ops.square(err), weights)
483 return (math_ops.reduce_sum(weighted_squared_err) /
484 (2.0 * math_ops.reduce_sum(weights)))
510 math_ops.reduce_sum(math_ops.cast(weights, dtypes.float64)) +
