/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

13 votes180 views4 answers
Panda dataframe to list
Python
0 vote234 views1 answer
How to extract field values in list from queryset in django
Python
11 votes195 views5 answers
Dataframe change index
Python
-1 vote180 views1 answer
Python delete file from directory
Python
0 vote200 views1 answer
Setting urls
Python
2 votes258 views1 answer
Python how to unnest a nested list
Python
0 vote195 views1 answer
How to make a grid list in python
Python
0 vote196 views1 answer
Unique file name in django
Python
1 vote324 views1 answer
Using df.astype to select categorical data and numerical data
Python
9 votes257 views1 answer
Sleep in python 3
Python