Tensorflow error: Using a `tf.Tensor` as a Python `bool` is not allowed

Question

I am struggling to implement an activation function in tensorflow in Python.

The code is the following:

def myfunc(x):
    if (x > 0):
        return 1
    return 0

But I am always getting the error:

Using a tf.Tensor as a Python bool is not allowed. Use if t is not None:

Innat · Accepted Answer · 2021-10-25 13:43:53Z

18

tf.cond(tf.greater(x, 0), lambda: 1, lambda: 0)

Another solution, which in addition supports multi-dimensional tensors:

tf.sign(tf.maximum(x, 0))

Note, however, that the gradient of this activation is zero everywhere, so the neural network won't learn anything with it.

Innat

17.3k6 gold badges60 silver badges115 bronze badges

answered Feb 1, 2018 at 20:53

Maxim

53.9k27 gold badges161 silver badges213 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

Unfortunately, I have this error now Shape must be rank 0 but is rank 2 for 'actfc1_36/activation_15/cond/Switch' (op: 'Switch') with input shapes

Innat · Accepted Answer · 2021-10-25 13:43:27Z

4

In TF2, you could just decorate the function myfunc() with @tf.function:

@tf.function
def myfunc(x):
    if (x > 0):
        return 1
    return 0

Innat

17.3k6 gold badges60 silver badges115 bronze badges

answered Sep 22, 2020 at 9:13

Ayush Garg

754 bronze badges