Multiple outputs in Keras gives value error - tensorflow

Question

I am implementing a modification of the U-net for semantic segmentation.
I have two outputs from the network :
model = Model(input=inputs, output= [conv10, dense3])
model.compile(optimizer=Adam(lr=1e-5), loss=common_loss, metrics=[common_loss])
where common loss is defined as :
def common_loss(y_true, y_pred):
segmentation_loss = categorical_crossentropy(y_true[0], y_pred[0])
classifiction_loss = categorical_crossentropy(y_true[1], y_pred[1])
return segmentation_loss + alpha * classifiction_loss
When I run this I get an value error as:
File "y-net.py", line 138, in <module>
train_and_predict()
File "y-net.py", line 133, in train_and_predict
callbacks=[model_checkpoint], validation_data=(X_val, [y_img_val, y_class_val]))
File "/home/gpu_users/meetshah/miniconda2/envs/check/lib/python2.7/site-packages/keras/engine/training.py", line 1124, in fit
callback_metrics=callback_metrics)
File "/home/gpu_users/meetshah/miniconda2/envs/check/lib/python2.7/site-packages/keras/engine/training.py", line 848, in _fit_loop
callbacks.on_batch_end(batch_index, batch_logs)
File "/home/gpu_users/meetshah/miniconda2/envs/check/lib/python2.7/site-packages/keras/callbacks.py", line 63, in on_batch_end
callback.on_batch_end(batch, logs)
File "/home/gpu_users/meetshah/miniconda2/envs/check/lib/python2.7/site-packages/keras/callbacks.py", line 191, in on_batch_end
self.progbar.update(self.seen, self.log_values)
File "/home/gpu_users/meetshah/miniconda2/envs/check/lib/python2.7/site-packages/keras/utils/generic_utils.py", line 147, in update
if abs(avg) > 1e-3:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
My implementation and the entire trace can be found here :
https://gist.github.com/meetshah1995/19d54270e8d1b20f814e6c1495facc6a

Answer 1

You can see how to implement multiple metrics with multiple outputs here: https://github.com/EdwardTyantov/ultrasound-nerve-segmentation/blob/master/u_model.py.
model.compile(optimizer=optimizer,
loss={'main_output': dice_coef_loss, 'aux_output': 'binary_crossentropy'},
metrics={'main_output': dice_coef, 'aux_output': 'acc'},
loss_weights={'main_output': 1., 'aux_output': 0.5})
I am not sure, if combined output metrics are supported yet.