array_ops

Tensor Transformations

---

Note: Functions taking Tensor arguments can also take anything accepted by [ tf.convert_to_tensor ]

Contents

---

Tensor Transformations

●Casting

○ tf.string_to_number(string_tensor, out_type=None, name=None)

○ tf.to_double(x, name='ToDouble')

○ tf.to_float(x, name='ToFloat')

○ tf.to_bfloat16(x, name='ToBFloat16')

○ tf.to_int32(x, name='ToInt32')

○ tf.to_int64(x, name='ToInt64')

○ tf.cast(x, dtype, name=None)

●Shapes and Shaping

○ tf.shape(input, name=None)

○ tf.size(input, name=None)

○ tf.rank(input, name=None)

○ tf.reshape(tensor, shape, name=None)

○ tf.squeeze(input, squeeze_dims=None, name=None)

○ tf.expand_dims(input, dim, name=None)

●Slicing and Joining

○ tf.slice(input_, begin, size, name=None)

○ tf.split(split_dim, num_split, value, name='split')

○ tf.tile(input, multiples, name=None)

○ tf.pad(input, paddings, name=None)

○ tf.concat(concat_dim, values, name='concat')

○ tf.pack(values, name='pack')

○ tf.unpack(value, num=None, name='unpack')

○ tf.reverse_sequence(input, seq_lengths, seq_dim, name=None)

○ tf.reverse(tensor, dims, name=None)

○ tf.transpose(a, perm=None, name='transpose')

○ tf.gather(params, indices, name=None)

○ tf.dynamic_partition(data, partitions, num_partitions, name=None)

○ tf.dynamic_stitch(indices, data, name=None)

---

Casting

TensorFlow provides several operations that you can use to cast tensor data types in your graph.

---

tf.string_to_number(string_tensor, out_type=None, name=None)

Converts each string in the input Tensor to the specified numeric type.

(Note that int32 overflow results in an error while float overflow results in a rounded value.)

Args:

     string_tensor: ATensorof typestring.

     out_type: An optionaltf.DTypefrom:tf.float32, tf.int32. Defaults totf.float32. The numeric type to interpret each      string in string_tensor as.

     name: A name for the operation (optional).

Returns:

     ATensorof typeout_type. A Tensor of the same shape as the input string_tensor.

Example:

#!/usr/bin/env python

# -*- coding: utf-8 -*-

import tensorflow as tf

import numpy as np

a = tf.constant('10.1')

c = tf.string_to_number(a)

sess = tf.Session()

print (sess.run(c))

sess.close()

---