Why my validation loss is not converging over multistream model?

Published: 14/01/2019
Why my validation loss is not converging over multistream model?
Source: STACKOVERFLOW.COM

I want to merge two CNNs that are trained over the different dataset. I have take two sequential models and merged them. But when using customized fit_generato, validation loss is not converging. How will I pass generators of different datasets? input1_1 = keras.layers.Input(shape=(129,129,3)) x1 = keras.layers.Conv2D(kernel_size = (3,3), filters = 32, activation='PReLU')(input1_1) x3 = keras.la

Read more
Related news
Comment
FACEBOOK