Course Content
TensorFlow Tutorial
    About Lesson

    Creating a Tensor

    Following is the way of creating a Tensor

    Syntax:

    tf.constant(value, dtype, name = "")

    Arguments:

    -`value`: Value of n-dimension to define the tensor.

    Optional –

    ‘dtype’ – Define the type of data:

    • `tf.string`: String variable
    • `tf.int16`: Integer variable
    • `tf.float32`: Flot variable
    • “name”: Name of the tensor.

    Optional:

    By default, `Const_1:0`

     

    To create a tensor of dimension 0

    import tensorflow as tf  
    r1 = tf.constant(1, tf.int16)   
    print(r1)  
    r2 = tf.constant(1, tf.int16, name = "my_scalar")   
    print(r2)

     

    The output of the above code will be Tensor(“Const_1:0”, shape=(), dtype=int16) Tensor(“my_scalar:0”, shape=(), dtype=int16)

     

    To create a tensor with decimal or string values

    import tensorflow as tf  
    # Decimal  
    r1_decimal = tf.constant(1.12345, tf.float32)  
    print(r1_decimal)  
    # String  
    r1_string = tf.constant("infovistar", tf.string)  
    print(r1_string)

     

    The output of the above code will be Tensor(“Const_2:0”, shape=(), dtype=float32) Tensor(“Const_3:0”, shape=(), dtype=string)

     

    To create a tensor of dimension 1

    import tensorflow as tf  
    r2_boolean = tf.constant([True, True, False], tf.bool)  
    print(r2_boolean)  
    ## Rank 2  
    r2_matrix = tf.constant([ [1, 2],  
                              [3, 4] ], tf.int16)  
    print(r2_matrix)

     

    The output of the above code will be Tensor(“Const_4:0”, shape=(3,), dtype=bool) Tensor(“Const_5:0”, shape=(2, 2), dtype=int16)