Error in creating custom initializer using get_variable with Keras

Question

I created a custom initializer with Keras. Part of the code is:

def my_init(shape):
    P = tf.get_variable("P", shape=shape,    initializer = tf.contrib.layers.xavier_initializer())
    return P

model = Sequential()
model.add(Conv2D(32, kernel_size=(5, 5),strides=(1, 1), padding='same', input_shape = input_shape, kernel_initializer = my_init))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, kernel_size=(1, 1) , strides=(1, 1) , padding='same' , kernel_initializer = my_init))

When "my_init" initializer is called for the second time in the convolution layer it throws this error:

Variable P already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:

It is not allowing to reuse the variable P. Is there any way to create a new variable in each call?

You could try K.variable(....). It doesn't require a name. --- import keras.backend as K. — Daniel Möller
– Daniel Möller, Commented Sep 25, 2017 at 14:28
I need to use "xavier" initializer available in tensorflow (tf.contrib.layers.xavier_initializer()) but k.variable is not allowing to call xavier initializer. — Darshi
– Darshi, Commented Sep 26, 2017 at 14:52

Daniel Möller · Accepted Answer · 2017-09-27 16:04:26Z

1

You could try using the Xavier initializers available in Keras, under the names glorot_uniform and glorot_normal.

See them here: https://keras.io/initializers/

model.add(Conv2D(32, kernel_size=(1, 1) , strides=(1, 1) , 
          padding='same' , kernel_initializer =keras.initializers.glorot_uniform())

edited Sep 27, 2017 at 16:04

answered Sep 27, 2017 at 15:59

Daniel Möller

86.8k24 gold badges202 silver badges222 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

W. Sam Over a year ago

how about initializing any variable to Xavier initializers, I mean not within Conv2D layer. for example: 'L1 = tf.keras.backend.variable( value= np.random.normal(0.0, 1.0, (feature_dim, feature_dim)), dtype= tf.float32) '. I want to initialize the same variable but using Xaivier initializer instead but couldn't find a proper way to do it.

Daniel Möller Over a year ago

Just call the initializer with the desired shape. L1 = keras.initializers.glorot_uniform()(shape)

Collectives™ on Stack Overflow

Error in creating custom initializer using get_variable with Keras

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related