Import TensorFlow and Numpy:
In [1]:
import tensorflow as tf
import numpy as np
Now, define a 2x2 matrix in different ways:
In [2]:
m1 = [[1.0, 2.0],
[3.0, 4.0]]
m2 = np.array([[1.0, 2.0],
[3.0, 4.0]], dtype=np.float32)
m3 = tf.constant([[1.0, 2.0],
[3.0, 4.0]])
Let's see what happens when we print them:
In [3]:
print(type(m1))
print(type(m2))
print(type(m3))
So, that's what we're dealing with. Interesting.
By the way, there's a function called convert_to_tensor(...) that does exactly what you might expect.
Let's use it to create tensor objects out of various types:
In [4]:
t1 = tf.convert_to_tensor(m1, dtype=tf.float32)
t2 = tf.convert_to_tensor(m2, dtype=tf.float32)
t3 = tf.convert_to_tensor(m3, dtype=tf.float32)
Ok, ok! Time for the reveal:
In [5]:
print(type(t1))
print(type(t2))
print(type(t3))