Shape of tensor

When you print the tensor, TensorFlow guesses the shape. However, you can get the shape of the tensor with the shape property.

Below, you construct a matrix filled with a number from 10 to 15 and you check the shape of m_shape

# Shape of tensor

m_shape = tf.constant([ [10, 11],

                        [12, 13],

                        [14, 15] ]                      

                     ) 

m_shape.shape                                   

Output

TensorShape([Dimension(3), Dimension(2)])                                            

The matrix has 3 rows and 2 columns.

TensorFlow has useful commands to create a vector or a matrix filled with 0 or 1. For instance, if you want to create a 1-D tensor with a specific shape of 10, filled with 0, you can run the code below:

# Create a vector of 0

print(tf.zeros(10))                                             

Output

Tensor("zeros:0", shape=(10,), dtype=float32)                                           

The property works for matrix as well. Here, you create a 10×10 matrix filled with 1

# Create a vector of 1

print(tf.ones([10, 10]))                                     

Output

Tensor("ones:0", shape=(10, 10), dtype=float32)                                      

You can use the shape of a given matrix to make a vector of ones. The matrix m_shape is a 3×2 dimensions. You can create a tensor with 3 rows filled by one’s with the following code:

# Create a vector of ones with the same number of rows as m_shape

print(tf.ones(m_shape.shape[0]))                                  

Output

Tensor("ones_1:0", shape=(3,), dtype=float32)                                          

If you pass the value 1 into the bracket, you can construct a vector of ones equals to the number of columns in the matrix m_shape.

# Create a vector of ones with the same number of column as m_shape

print(tf.ones(m_shape.shape[1]))                                  

Output

Tensor("ones_2:0", shape=(2,), dtype=float32)                                          

Finally, you can create a matrix 3×2 with only one’s

print(tf.ones(m_shape.shape))                                        

Output

Tensor("ones_3:0", shape=(3, 2), dtype=float32)