def gaussian_exp(inp_val):
"""
Expand values to gaussian basis
"""
guass_filter = tf.range(-5, 5 + 1, 1)
return tf.math.exp(-(tf.expand_dims(inp_val, axis=-1) - guass_filter)**2 /(1**2))
The above code works fine for integer values, but gives an error while processing float values, any idea?