How to have parallel convolutional layers in keras?

Question

I am a little new to neural networks and keras. I have some images with size 6*7 and the size of the filter is 15. I want to have several filters and train a convolutional layer separately on each and then combine them. I have looked at one example here:

model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                    border_mode='valid',
                    input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))

This model works with one filter. Can anybody give me some hints on how to modify the model to work with parallel convolutional layers.

Thanks

score 41 · Answer 1 · answered Jul 25 '17 at 13:01

Here is an example of designing a network of parallel convolution and sub sampling layers in keras version 2. I hope this resolves your problem.

rows, cols = 100, 15
def create_convnet(img_path='network_image.png'):
    input_shape = Input(shape=(rows, cols, 1))

    tower_1 = Conv2D(20, (100, 5), padding='same', activation='relu')(input_shape)
    tower_1 = MaxPooling2D((1, 11), strides=(1, 1), padding='same')(tower_1)

    tower_2 = Conv2D(20, (100, 7), padding='same', activation='relu')(input_shape)
    tower_2 = MaxPooling2D((1, 9), strides=(1, 1), padding='same')(tower_2)

    tower_3 = Conv2D(20, (100, 10), padding='same', activation='relu')(input_shape)
    tower_3 = MaxPooling2D((1, 6), strides=(1, 1), padding='same')(tower_3)

    merged = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
    merged = Flatten()(merged)

    out = Dense(200, activation='relu')(merged)
    out = Dense(num_classes, activation='softmax')(out)

    model = Model(input_shape, out)
    plot_model(model, to_file=img_path)
    return model

The image of this network will look like

this is exactly what I was looking for. If u are still active can u reply here for a few more questions — Ansh David, Sep 16 '17 at 18:37
Hey @durjoy Could you please look into this issue https://stackoverflow.com/q/61734815/10665645 — monica, May 15 '20 at 17:30

score 20 · Accepted Answer · edited Apr 29 '19 at 22:56

My approach is to create other model that defines all parallel convolution and pulling operations and concat all parallel result tensors to single output tensor. Now you can add this parallel model graph in your sequential model just like layer. Here is my solution, hope it solves your problem.

# variable initialization 
from keras import Input, Model, Sequential
from keras.layers import Conv2D, MaxPooling2D, Concatenate, Activation, Dropout, Flatten, Dense

nb_filters =100
kernel_size= {}
kernel_size[0]= [3,3]
kernel_size[1]= [4,4]
kernel_size[2]= [5,5]
input_shape=(32, 32, 3)
pool_size = (2,2)
nb_classes =2
no_parallel_filters = 3

# create seperate model graph for parallel processing with different filter sizes
# apply 'same' padding so that ll produce o/p tensor of same size for concatination
# cancat all paralle output

inp = Input(shape=input_shape)
convs = []
for k_no in range(len(kernel_size)):
    conv = Conv2D(nb_filters, kernel_size[k_no][0], kernel_size[k_no][1],
                    border_mode='same',
                         activation='relu',
                    input_shape=input_shape)(inp)
    pool = MaxPooling2D(pool_size=pool_size)(conv)
    convs.append(pool)

if len(kernel_size) > 1:
    out = Concatenate()(convs)
else:
    out = convs[0]

conv_model = Model(input=inp, output=out)

# add created model grapg in sequential model

model = Sequential()
model.add(conv_model)        # add model just like layer
model.add(Conv2D(nb_filters, kernel_size[1][0], kernel_size[1][0]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten(input_shape=input_shape))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('tanh'))

For more information refer similar question: Combining the outputs of multiple models into one model

I think that is useful. I will definitely try it. Just a quick question, Is Model the other class which contains a sequential model? What should be the output? — ida, Apr 02 '17 at 23:22
No, it's not sequential. Sequential model defines simple network architectures, it takes single input and produce single output and pass it to next layer in sequence, dimensions of tensors depends on layers in model. For defining complex architecture you need to use other functional API's for model. You can find more details in keras documentation https://keras.io/getting-started/functional-api-guide/ — Nilesh Birari, Apr 03 '17 at 07:15

How to have parallel convolutional layers in keras?

2 Answers2

Linked