/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

0 vote383 views1 answer
Def f(x) python
Python
0 vote331 views1 answer
Pandas fillna with median of column
Python
1 vote347 views1 answer
Missingpy No module named 'sklearn.neighbors.base'
Python
4 votes337 views1 answer
'numpy.ndarray' object has no attribute 'append'
Python
0 vote314 views2 answers
I type nano in python and o get error
Python
0 vote305 views9 answers
Python code checker and corrector
Python
0 vote383 views1 answer
Creating a frequency table | generating a frequency table
Python
2 votes353 views2 answers
How to call a specific item from a list python
Python
0 vote335 views1 answer
Expected a list of items but got type int . django
Python
5 votes353 views2 answers
Stitch two dictionary python
Python