How to show combined overall accuracy for a multi-ouput model in Keras?

I have a model of the following structure. It has 6 outputs. Given an image, the model predicts classes of 6 different components from the image.

The metrics I used are:

As you can see it outputs an overall combined loss and separate losses for different outputs. But there is no combined accuracy score. What I want is a combined accuracy score ( Which will consider a sample is correct if all the output labels are correct). How can I calculate overall combined accuracy for my multioutput model?

Topic multi-output metric cnn multilabel-classification accuracy

Category Data Science

1
answered at

Tensroflow has a built-in metric for accuracy. Add this line to 'metrices' in your code:

'acc':[tf.keras.metrics.Accuracy()]

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.