I realized I am required to use root mean squared error for my loss fuction, but RMSE does not exist in tf.keras.losses. I have trained a model using MSE, is this acceptable or do I have to define my own RMSE loss function?
It just means that our predictions will be ranked based on rmse scores from actual. You can train with any metric of choice.
Thank you.
It just means that our predictions will be ranked based on rmse scores from actual. You can train with any metric of choice.
Thank you.