A.M.
A.M.

Reputation: 1797

Theano HiddenLayer Activation Function

Is there anyway to use Rectified Linear Unit (ReLU) as the activation function of the hidden layer instead of tanh() or sigmoid() in Theano? The implementation of the hidden layer is as follows and as far as I have searched on the internet ReLU is not implemented inside the Theano.

class HiddenLayer(object):
  def __init__(self, rng, input, n_in, n_out, W=None, b=None, activation=T.tanh):
    pass

Upvotes: 11

Views: 9219

Answers (5)

Not a machine
Not a machine

Reputation: 551

The function is very simple in Python:

def relu(input):
    output = max(input, 0)
    return(output)

Upvotes: 0

nouiz
nouiz

Reputation: 5071

relu is easy to do in Theano:

switch(x<0, 0, x)

To use it in your case make a python function that will implement relu and pass it to activation:

def relu(x):
    return theano.tensor.switch(x<0, 0, x)
HiddenLayer(..., activation=relu)

Some people use this implementation: x * (x > 0)

UPDATE: Newer Theano version have theano.tensor.nnet.relu(x) available.

Upvotes: 17

Alleo
Alleo

Reputation: 8548

UPDATE: Latest version of theano has native support of ReLU: T.nnet.relu, which should be preferred over custom solutions.

I decided to compare the speed of solutions, since it is very important for NNs. Compared speed of function itself and it's gradient, in first case switch is preferred, the gradient is faster for x * (x>0). All the computed gradients are correct.

def relu1(x):
    return T.switch(x<0, 0, x)

def relu2(x):
    return T.maximum(x, 0)

def relu3(x):
    return x * (x > 0)


z = numpy.random.normal(size=[1000, 1000])
for f in [relu1, relu2, relu3]:
    x = theano.tensor.matrix()
    fun = theano.function([x], f(x))
    %timeit fun(z)
    assert numpy.all(fun(z) == numpy.where(z > 0, z, 0))

Output: (time to compute ReLU function)
>100 loops, best of 3: 3.09 ms per loop
>100 loops, best of 3: 8.47 ms per loop
>100 loops, best of 3: 7.87 ms per loop

for f in [relu1, relu2, relu3]:
    x = theano.tensor.matrix()
    fun = theano.function([x], theano.grad(T.sum(f(x)), x))
    %timeit fun(z)
    assert numpy.all(fun(z) == (z > 0)

Output: time to compute gradient 
>100 loops, best of 3: 8.3 ms per loop
>100 loops, best of 3: 7.46 ms per loop
>100 loops, best of 3: 5.74 ms per loop

Finally, let's compare to how gradient should be computed (the fastest way)

x = theano.tensor.matrix()
fun = theano.function([x], x > 0)
%timeit fun(z)
Output:
>100 loops, best of 3: 2.77 ms per loop

So theano generates inoptimal code for gradient. IMHO, switch version today should be preferred.

Upvotes: 8

grin
grin

Reputation: 109

I wrote it like this:

lambda x: T.maximum(0,x)

or:

lambda x: x * (x > 0)

Upvotes: 1

user4175155
user4175155

Reputation:

I think it is more precise to write it in this way:

x * (x > 0.) + 0. * (x < 0.)

Upvotes: 1

Related Questions