/Python/When training= false still dropout

When training= false still dropout

from keras import layers
from keras import models
from keras import backend as K
import numpy as np

inp = layers.Input(shape=(10,))
out = layers.Dropout(0.5)(inp)

model = models.Model(inp, out)
model.layers[-1].trainable = False  # set dropout layer as non-trainable
model.compile(optimizer='adam', loss='mse') # IMPORTANT: we must always compile model after changing `trainable` attribute

# create a custom backend function so that we can control the learning phase
func = K.function(model.inputs + [K.learning_phase()], model.outputs)

x = np.ones((1,10))
# learning phase = 1, i.e. training mode
print(func([x, 1]))
# the output will be:
[array([[2., 2., 2., 0., 0., 2., 2., 2., 0., 0.]], dtype=float32)]
# as you can see some of the neurons have been dropped

# now set learning phase = 0, i.e test mode
print(func([x, 0]))
# the output will be:
[array([[1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]], dtype=float32)]
# unsurprisingly, no neurons have been dropped in test phase

Source: stackoverflow.com

Similar codes

0 vote328 views1 answer
Python list pop equivalent
Python
1 vote355 views1 answer
Flask socketio send
Python
0 vote404 views1 answer
Activate inherit function django
Python Django
0 vote329 views1 answer
Python change recursion depth
Python
50 votes291 views1 answer
Append to the start of a list python
Python
6 votes344 views1 answer
Numpy round
Python
0 vote367 views1 answer
Unpersist cache pyspark
Python
35 votes368 views6 answers
Python generate random string
Python
0 vote407 views1 answer
Django insert bulk data
Python Django
3 votes381 views2 answers
Merge sort of two list in python
Python