Home/ Questions/Q 1824
Next
In Process
Peggy
  • 0
Professional
Asked: 2023-07-05T03:17:08+00:00 In:

In Keras, how do you calculate precision and recall?

  • 0

I’m using Tensorflow 2 to train a binary classification model. I pass the metrics [‘accuracy,’ tf.keras.metrics.Precision()  tf.keras.metrics.Recall()] but accuracy, precision, and recall are all the same at every point in time. How to calculate precision and recall correctly?

Data EngineeringkerasTensorFlow
Share
Leave an answer

Leave an answer

Browse

1 Answer

  1. Pundit

    For Keras version 2 precision and recall were removed from the master branch. Whereas in version 2.3.0 they are provided with library package. You can try using later version.

     

    tf.keras.metrics.Precision(
    thresholds=None, top_k=None, class_id=None, name=None, dtype=None
)
    tf.keras.metrics.Recall(
    thresholds=None, top_k=None, class_id=None, name=None, dtype=None
)

    you can also refer to the metrics in keras.io

    • 0