/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 votes250 views1 answer
Randonm forest python
Python
37 votes313 views1 answer
Time format conversion in python
Python
1 vote320 views1 answer
Get all keys and values from dictionary python
Python
0 vote335 views1 answer
Python import from string name
Python
0 vote323 views1 answer
Readme python convert to pdf
Python
19 votes351 views6 answers
Add item to python list
Python
49 votes345 views2 answers
Add new element to python dictionary
Python
9 votes265 views1 answer
How to delete everything in a text file python
Python
2 votes311 views1 answer
Python how to check which int var is the greatest
Python
0 vote313 views1 answer
Python library automatic sort
Python