[TensorFlow] Tensor

1) Tensor 자료형을 constant를 이용하여 생성

import tensorflow as tf
 
const = tf.constant('Hello Tensorflow!!!')
print(const)

>> Tensor("Const:0", shape=(), dtype=string)

2) Tensor 자료형은 python에서 호출 불가능, 따라서 Tensorflow에서 제공하는 Session() 함수의 run을 통해 호출 가능

import tensorflow as tf
 
const = tf.constant('Hello Tensorflow!!!')
 
with tf.Session() as sess:
    _const = sess.run(const)
    print(_const)

>> b'Hello Tensorflow!!!'

3) Tensorflow를 사용한 Matrix 연산 예제

import tensorflow as tf
 
mat1 = [[1, 2, 3,], [4, 5, 6], [7, 8, 9]]
mat2 = [[2, 2, 2,], [2, 2, 2], [2, 2, 2]]
 
t_mat1 = tf.constant(mat1)
t_mat2 = tf.constant(mat2)
 
result = tf.matmul(t_mat1, t_mat2)
 
with tf.Session() as sess:
    _result = sess.run(result)

>> [[12 12 12]

[30 30 30]

[48 48 48]]

Rank

Rank	Math entity	Python example
0	Scalar (magnitude only)	s = 123
1	Vector (magnitude and direction)	v = [1.1 , 2.2]
2	Matrix (table of numbers)	m = [[1, 2, 3], [4, 5, 6]]
3	3-Tensor (cube of numbers)	t = [[[1], [2], [3]], [[4], [5], [6]], [[7], [8], [9]]]
n	n-Tensor (you get the idea)	. . . .

Shape

Rank	Shape	Dimension number	Example
0	[]	0-D	A 0-D tensor. A scalar.
1	[D0]	1-D	A 1-D tensor with shape [3].
2	[D0, D1]	2-D	A 2-D tensor with shape [1, 2].
3	[D0, D1, D2]	3-D	A 3-D tensor with shape [1, 2, 3].
n	[D0, D1, ... Dn-1]	n-D	A tensor with shape [D0, D1, ... Dn-1].

Type

Data type	Python type	Description
DT_FLOAT	tf.float32	32 bits floating point.
DT_DOUBLE	tf.float64	64 bits floating point.
DT_INT8	tf.int8	8 bits signed integer.
DT_INT16	tf.int16	16 bits signed integer.
DT_INT32	tf.int32	32 bits signed integer.
DT_INT34	tf.int64	64 bits signed integer.