Enhancing Model Selection with Custom Metrics
Understand how to enhance model selection for Multi-Layer Perceptrons by creating custom metrics in TensorFlow. Explore the programmatic steps to define and compute specialized metrics such as FalsePositiveRate and F1Score, which provide deeper insights into model performance across training epochs. This lesson helps you tailor metric evaluation to improve model selection for rare event prediction.
We'll cover the following...
Metrics customization
Looking at suitably chosen metrics for a problem tremendously increases the ability to develop better models. Although a metric does not directly improve model training, it helps in a better model selection.
Several metrics are available outside TensorFlow, such as in sklearn. However, they can’t be used directly during model training in TensorFlow. This is because the metrics are computed while processing batches during each training epoch.
Fortunately, TensorFlow provides the ability for this customization. The custom-defined metrics F1Score and FalsePositiveRate are provided ...