Keras: Feeding In Part Of Previous Layer To Next Layer, In Cnn

I am trying to feed in the individual kernel outputs of the previous layer to a new conv filter, to get the next layer. To do that, I tried passing each of the kernel outputs throu

Solution 1:

After posting this and this questions in StackOverflow, and some personal exploring, I came up with a solution. One can possibly do this with Lambda layers; by calling a Lambda layer to extract a sub part of the previous layer. For example, if the Lambda function is defined as,

deflayer_slice(x,i):
    return x[:,:,:,i:i+1]

and then, called as,

k = 5
x = Conv2D(k, (3,3), data_format='channels_last', padding='same', name='block1_conv1')(inputs)
y = np.empty(k, dtype=object)
for i inrange(0,k):
    y[i] = Lambda(layer_slice, arguments={'i':i})(x)
    y[i] = Conv2D(1,(3,3), data_format='channels_last', padding='same')(y[i])
y = keras.layers.concatenate([y[i] for i inrange (0,k)], axis=3, name='block1_conv1_loc')
out = Activation('relu')(y)
print ('Output shape is, ' +str(out.get_shape()))

it should effectively feed in individual kernel outputs to a new Conv2D layer. The layer shapes and corresponding number of trainable parameters being obtained from model.summary() matches the expectation. Thanks to Daniel for pointing out that Lambda layers cannot have trainable weights.

Solution 2:

Prabaha. I know you've solved your problem, but now I see your answer, you can do that without using the lambda layer too, just split the first Conv2D in many. One layer with k filters is equivalent to k layers with one filter:

for i in range(0,k):
    y[i] = Conv2D(1, (3,3), ... , name='block1_conv'+str(i))(inputs)     
    y[i] = Conv2D(1,(3,3), ...)(y[i])
y = Concatenate()([y[i] for i in range (0,k)])
out = Activation('relu')(y)

You can count the total parameters in your answer and in this answer to compare.