/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

1 vote306 views1 answer
Variable plus one python
Python
0 vote391 views1 answer
Error: The file/path provided (flaskr) does not appear to exist. Please verify the path is correct. If app is not on PYTHONPATH, ensure the extension is .py
Python Flask
0 vote334 views1 answer
Jupyter notebook fancy print cross tab
Python
2 votes318 views1 answer
Python find specific file in directory
Python
24 votes313 views1 answer
Python datetime strptime hour minute second
Python
1 vote284 views1 answer
How to manke a query in google api freebusy python
Python
67 votes307 views4 answers
List slicing reverse python
Python
7 votes320 views1 answer
How to set the screen brightness using python
Python
0 vote298 views1 answer
How to sort the dataframe in python by axis
Python
3 votes284 views1 answer
Python copy a dictionary to a new variable
Python