Three ways to use custom validation metrics in tf.keras / TF2
How to use custom validation metrics in TensorFlow 2
Published in
3 min readSep 28, 2020
Keras offers a bunch of metrics to validate the test data set like accuracy, MSE or AUC. However, sometimes you need a custom metric to validate your model. In this post, I will show three different approaches to implement your metrics and use it within Keras.