/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

8 votes212 views2 answers
Lambda function with if elif else python
Python
0 vote156 views1 answer
Recurrent neural network pytorch
Python
0 vote140 views2 answers
Pygame center text in rect
Python
16 votes100 views1 answer
Add to index python
Python
24 votes156 views6 answers
How to save a pickle file
Python
0 vote148 views1 answer
Argsort in descending order numpy
Python
0 vote143 views1 answer
Cursor.fetchall() to list
Python
0 vote153 views1 answer
Select only some rows pandas
Python
-1 vote140 views2 answers
Hierarchical clustering Agglomerative
Python
0 vote135 views1 answer
How to add to beginning of linked list python
Python