/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 vote157 views1 answer
Creating base models django
Python
-2 votes134 views1 answer
Center buttons tkinter
Python
4 votes163 views2 answers
Python regex group
Python
0 vote179 views1 answer
List to string without loop
Python
0 vote139 views1 answer
List the contents of a package python
Python
0 vote130 views1 answer
Django set boolean field value in view
Python Django
3 votes137 views2 answers
Python remove cached package
Python
0 vote130 views2 answers
Staircase hackerrank solution python
Python
0 vote144 views1 answer
How to import api keys
Python
3 votes129 views4 answers
List in pythom
Python