Handling more than one output, but only one loss about livelossplot HOT 3 CLOSED

I see. Apparently I would need to loop through output names, in addition to losses (though: are many losses a typical thing?).

To do the whole thing - https://github.com/keras-team/keras/blob/master/keras/engine/training.py is a bit convolved.

If you want to give it a try, you are welcome (feel free to change this piece of code a lot - as I said, didn't test it so don't be afraid of a complete rewrite of this part).

from livelossplot.

@jonahweissman I admit I didn't test livelossplot with multiple losses. I wrote based on my understanding on how does Keras deal with multiple losses.

Could you show me the line with model.compile and the result of model.loss, model.output_names (and possibly, what is in logs)?

from livelossplot.

Here's my line with model.compile (I'm using the functional API):

model = Model(inputs=[weather_layers[0], day_layers[0], date_layers[0]], outputs=[usage_out,clients_out,sessions_out])
model.compile(loss='mean_absolute_percentage_error',
              optimizer=Adam(0.0001))

In [1]: model.loss
Out[1]: 'mean_absolute_percentage_error'

In [2]: model.output_names
Out[2]: ['usage', 'clients', 'sessions']

In [3]: model.losses
Out[3]: []

I didn't specify loss functions for each output, so I believe it uses model.loss for each.

from livelossplot.