How can I create a model which is starts with a single convolution layer and then its output given to two different convolution layers

Question

Can I generate a Model in keras which is not sequencial, i.e can I design a model with two train of cascaded convolution layer but the starting input is a common convolution output.

score 1 · Answer 1 · answered Jun 13 '17 at 13:18

1

Yes! You just need to use the Functional API.

e.g.

main_input = Input(shape=input_shape)

conv_1 = Conv1D(32, 3)(main_input)

conv_2 = Conv1D(64, 3)(conv_1)

conv_3 = Conv1d(64, 3)(conv_1)

answered Jun 13 '17 at 13:18

Michele Tonutti

4,298
1
21
22

How can I create a model which is starts with a single convolution layer and then its output given to two different convolution layers

1 Answers1