/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 votes288 views1 answer
Remove all pycache files
Python
0 vote269 views1 answer
Nltk regex parser
Python
2 votes254 views2 answers
Int' object is not subscriptable in python
Python
0 vote1.3K views1 answer
Python doctype
Python
71 votes305 views6 answers
Virtual env in python
Python
4 votes278 views3 answers
Python vs Java
Python
28 votes296 views3 answers
Seaborn size
Python
1 vote264 views1 answer
Wonsan
Python
0 vote300 views1 answer
How to change dtype object to int
Python
0 vote295 views1 answer
Start virtualenv with python version
Python