CODEWITHSUNDEEP
pythontensorflowkeras
Fra
Fra

Reputation: 5188

Merge Variables in Keras

I'm building a convolutional neural network with Keras and would like to add a single node with the standard deviation of my data before the last fully connected layer.

Here's a minimum code to reproduce the error:

from keras.layers import merge, Input, Dense
from keras.layers import Convolution1D, Flatten
from keras import backend as K

input_img = Input(shape=(64, 4))

x = Convolution1D(48, 3, activation='relu', init='he_normal')(input_img)
x = Flatten()(x)

std = K.std(input_img, axis=1)
x = merge([x, std], mode='concat', concat_axis=1)

output =  Dense(100, activation='softmax', init='he_normal')(x)

This results in the following TypeError:

-----------------------------------------------------------------
TypeError                       Traceback (most recent call last)
<ipython-input-117-c1289ebe610e> in <module>()
      6 x = merge([x, std], mode='concat', concat_axis=1)
      7 
----> 8 output =  Dense(100, activation='softmax', init='he_normal')(x)

/home/ubuntu/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/engine/topology.pyc in __call__(self, x, mask)
    486                                     '`layer.build(batch_input_shape)`')
    487             if len(input_shapes) == 1:
--> 488                 self.build(input_shapes[0])
    489             else:
    490                 self.build(input_shapes)

/home/ubuntu/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/layers/core.pyc in build(self, input_shape)
    701 
    702         self.W = self.init((input_dim, self.output_dim),
--> 703                            name='{}_W'.format(self.name))
    704         if self.bias:
    705             self.b = K.zeros((self.output_dim,),

/home/ubuntu/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/initializations.pyc in he_normal(shape, name, dim_ordering)
     64     '''
     65     fan_in, fan_out = get_fans(shape, dim_ordering=dim_ordering)
---> 66     s = np.sqrt(2. / fan_in)
     67     return normal(shape, s, name=name)
     68 

TypeError: unsupported operand type(s) for /: 'float' and 'NoneType'

Any idea why?

Upvotes: 3

Views: 552

Answers (1)

nemo
nemo

Reputation: 57639

std is no Keras layer so it does not satisfy the layer input/output shape interface. The solution to this is to use a Lambda layer wrapping K.std:

from keras.layers import merge, Input, Dense, Lambda
from keras.layers import Convolution1D, Flatten
from keras import backend as K

input_img = Input(shape=(64, 4))

x = Convolution1D(48, 3, activation='relu', init='he_normal')(input_img)
x = Flatten()(x)

std = Lambda(lambda x: K.std(x, axis=1))(input_img)
x = merge([x, std], mode='concat', concat_axis=1)

output =  Dense(100, activation='softmax', init='he_normal')(x)

Upvotes: 1

Related Questions