tf.math.add  |  TensorFlow v2.16.1 (original) (raw)

tf.math.add

Stay organized with collections Save and categorize content based on your preferences.

Returns x + y element-wise.

View aliases

Main aliases

tf.add

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.add

tf.math.add(
    x, y, name=None
)

Used in the notebooks

Example usages below.

Add a scalar and a list:

x = [1, 2, 3, 4, 5] y = 1 tf.add(x, y) <tf.Tensor: shape=(5,), dtype=int32, numpy=array([2, 3, 4, 5, 6], dtype=int32)>

Note that binary + operator can be used instead:

x = tf.convert_to_tensor([1, 2, 3, 4, 5]) y = tf.convert_to_tensor(1) x + y <tf.Tensor: shape=(5,), dtype=int32, numpy=array([2, 3, 4, 5, 6], dtype=int32)>

Add a tensor and a list of same shape:

x = [1, 2, 3, 4, 5] y = tf.constant([1, 2, 3, 4, 5]) tf.add(x, y) <tf.Tensor: shape=(5,), dtype=int32, numpy=array([ 2, 4, 6, 8, 10], dtype=int32)>

For example,

x = tf.constant([1, 2], dtype=tf.int8) y = [2**7 + 1, 2**7 + 2] tf.add(x, y) <tf.Tensor: shape=(2,), dtype=int8, numpy=array([-126, -124], dtype=int8)>

When adding two input values of different shapes, Add follows NumPy broadcasting rules. The two input array shapes are compared element-wise. Starting with the trailing dimensions, the two dimensions either have to be equal or one of them needs to be 1.

For example,

x = np.ones(6).reshape(1, 2, 1, 3) y = np.ones(6).reshape(2, 1, 3, 1) tf.add(x, y).shape.as_list() [2, 2, 3, 3]

Another example with two arrays of different dimension.

x = np.ones([1, 2, 1, 4]) y = np.ones([3, 4]) tf.add(x, y).shape.as_list() [1, 2, 3, 4]

The reduction version of this elementwise operation is tf.math.reduce_sum