0

I want to combine more types of activations in output layer in Keras interface for R. Also, I want to use different loss functions for different outputs. Lets say I want to have first two neurons linear with MSE loss, second 2 neurons sigmoid with BCE loss and last output will be relu with MAE loss. By now I have this and it is not working: 

model <- keras_model_sequential()

model %>% layer_dense(units=120, activation="selu", 
           input_shape=dim(X)[2]) # this is hidden layer, this works fine

model %>% layer_dense(units=120, activation=as.list(c(rep("linear",2), 
            rep("sigmoid",2), "relu"))) # output layer which is not working

model %>% compile(loss=as.list(c(rep("mean_squared_error",2), 
             rep("binary_crossentropy",2), "mean_absolute_error")), # problem here ?
             optimizer=optimizer_adam(lr=0.001) ,metrics = "mae")

and after this I fit the model with model %>% fit(...) .

Error is the following: 

Error in py_call_impl(callable, dots$args, dots$keywords) : 
  ValueError: When passing a list as loss, it should have one entry per model outputs. 
  The model has 1 outputs, but you passed loss=['mean_squared_error', 'mean_squared_error', ...

Any help is appreciated.

EDIT : only rewrited code so that is better readable.

pikachu
  • 690
  • 1
  • 6
  • 17

1 Answers1

1

I think that if you want to have multiple outputs you need to use the functional (that is, not the sequential) API - see some examples here: https://keras.rstudio.com/articles/functional_api.html

Valeri Voev
  • 1,982
  • 9
  • 25
  • Would the difference then be only in implementation, or also in math behind? Thanks. – pikachu Nov 19 '19 at 13:51
  • I think the math is the same - the functional API is just much more flexible than the sequential, which (as its name suggests) only allows to build sequential networks where layers feed linearly into the next one. You can do everything that is possible with the sequential API using the functional API, but you can du much more with the latter. – Valeri Voev Nov 19 '19 at 13:54