tf.linspace

Generates evenly-spaced values in an interval along a given axis.

Used in the notebooks

Used in the guide Used in the tutorials

A sequence of num evenly-spaced values are generated beginning at start along a given axis. If num > 1, the values in the sequence increase by (stop - start) / (num - 1), so that the last one is exactly stop. If num <= 0, ValueError is raised.

Matches np.linspace's behaviour except when num == 0.

For example:

tf.linspace(10.0, 12.0, 3, name="linspace") => [ 10.0  11.0  12.0]

Start and stop can be tensors of arbitrary size:

tf.linspace([0., 5.], [10., 40.], 5, axis=0)
<tf.Tensor: shape=(5, 2), dtype=float32, numpy=
array([[ 0.  ,  5.  ],
       [ 2.5 , 13.75],
       [ 5.  , 22.5 ],
       [ 7.5 , 31.25],
       [10.  , 40.  ]], dtype=float32)>

Axis is where the values will be generated (the dimension in the returned tensor which corresponds to the axis will be eq