jcarta

> Finally got it to work. Here are the changes! The issue with more than one class is that you need to compare it with categorical cross-entropy. But in Keras...

> `hist = model.fit_generator(trainGene, validation_data=validGene, validation_steps=3, steps_per_epoch=step_epoch, epochs=epochs, verbose=2, shuffle=True, callbacks=[model_checkpoint,tensorboard,history])` > I solved the problem by writing this way. Hope helpful to someone. What does your validGene implementation look...

> > > `hist = model.fit_generator(trainGene, validation_data=validGene, validation_steps=3, steps_per_epoch=step_epoch, epochs=epochs, verbose=2, shuffle=True, callbacks=[model_checkpoint,tensorboard,history])` > > > I solved the problem by writing this way. Hope helpful to someone. > >...

> > > > > `hist = model.fit_generator(trainGene, validation_data=validGene, validation_steps=3, steps_per_epoch=step_epoch, epochs=epochs, verbose=2, shuffle=True, callbacks=[model_checkpoint,tensorboard,history])` > > > > > I solved the problem by writing this way. Hope helpful...

This worked for me... // initialize login screen using AWS Drop-In Auth UI AWSMobileClient.getInstance().initialize(getApplicationContext(), new Callback() { @Override public void onResult(UserStateDetails userStateDetails) { Log.i("INIT", "onResult: " + userStateDetails.getUserState()); showSignIn(); }...

Was this confirmed to be an issue? If so, will an update be coming out?