How to turn off dropout for testing in Tensorflow?

user_8256202 0
Viewed 27666

I am fairly new to Tensorflow and ML in general, so I hereby apologize for a (likely) trivial question.

I use the dropout technique to improve learning rates of my network, and it seems to work just fine. Then, I would like to test the network on some data to see if it works like this:

   def Ask(self, image):
        return self.session.run(self.model, feed_dict = {self.inputPh: image})

Obviously, it yields different results each time as the dropout is still in place. One solution I can think of is to create two separate models - one for a training and the other one for an actual later use of the network, however, such a solution seems impractical to me.

What's the common approach to solving this problem?

conv-neural-network tensorflow machine-learning neural-network python
6 Answers

With the update of Tensorflow, the class tf.layer.dropout should be used instead of tf.nn.dropout.

This supports an is_training parameter. Using this allows your models to define keep_prob once, and not rely on your feed_dict to manage the external parameter. This allows for better refactored code.

More info: https://www.tensorflow.org/api_docs/python/tf/layers/dropout

user_55730740

When you test you are supposed to multiply the output of the layer by 1/drop_prob.

In that case you would have to put an additional multiplication step in the test phase.

user_115069760
Related