/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

4 votes108 views3 answers
Python os
Python
2 votes118 views1 answer
Comparing file content in python
Python
2 votes121 views2 answers
Discord.py ping command
Python
0 vote151 views1 answer
Setting up a django prostgress project
Python Django
0 vote162 views1 answer
Qt line edit set text python
Python
0 vote124 views1 answer
How to fix invalid salt in python flask
Python
0 vote111 views1 answer
PY | websocket - client
Python
21 votes133 views3 answers
Python ceiling division
Python
24 votes114 views2 answers
How to find the data type in python
Python
0 vote227 views1 answer
Django.com
Python