tf.zeros_like

Creates a tensor with all elements set to zero.

Used in the notebooks

Used in the guideUsed in the tutorials

See also tf.zeros.

Given a single tensor or array-like object (input), this operation returns a tensor of the same type and shape as input with all elements set to zero. Optionally, you can use dtype to specify a new type for the returned tensor.

Note that the layout of the input tensor is not preserved if the op is used inside tf.function. To obtain a tensor with the same layout as the input, chain the returned value to a dtensor.relayout_like.

>>> tensor = tf.constant([[1, 2, 3], [4, 5, 6]])
>>> tf.zeros_like(tensor)
<tf.Tensor: shape=(2, 3), dtype=int32, numpy=
array([[0, 0, 0],
       [0, 0, 0]], dtype=int32)>
tf.zeros_like(tensor, dtype=tf.float32)
<tf.Tensor: shape=(2, 3), dtype=float32, numpy=
array([[0., 0., 0.],
       [0., 0., 0.]], dtype=float32)>
tf.zeros_like([[1, 2, 3], [4, 5, 6]])
<tf.Tensor: shape=(2, 3), dtype=int32, numpy=
array([[0, 0, 0],
       [0, 0, 0]], dtype=int32)>

inputA Tensor or array-like object.
dtypeA type for the returned Tensor. Must be float16, float32, float64, int8, uint8, int16, uint16, int32, int64, complex64, complex128, bool or string (optional).
nameA name for the operation (optional).
layoutOptional, tf.experimental.dtensor.Layout. If provided, the result is a DTensor with the provided layout.

A Tensor with all elements set to zero.