/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

3 votes100 views1 answer
Python change plot transparency
Python
0 vote99 views1 answer
Django form label in template
Python
3 votes61 views1 answer
Endswith python
Python
0 vote101 views2 answers
Python how to extract a string from another string
Python
1 vote111 views1 answer
Pandas groupby size column name
Python
0 vote119 views1 answer
Mechanize python #9
Python
0 vote96 views1 answer
Cv2.imwrite save to folder
Python
1 vote99 views1 answer
List shape python
Python
0 vote100 views1 answer
Python append to tuple list
Python
3 votes123 views2 answers
Print first word of a string python and return it
Python