add a validation data option (validation_data)

david-thrower / cerebros-core-algorithm-alpha

The Cerebros package is an ultra-precise Neural Architecture Search (NAS) / AutoML that is intended to much more closely mimic biological neurons than conventional neural network architecture strategies.

Other

27 stars 4 forks source link

add a validation data option (validation_data) #99

Closed david-thrower closed 1 year ago

david-thrower commented 1 year ago

Kind of issue: feature-request-or-enhancement: Add a parameter validation_data: default: "", which is translated to None on self.validation_data

Need a parameter to forward validation data to the TensorFlow API
- self.validation_data -> tf.keras.Model.fit(validation_split=0.0, validation_data=[self.validation_data], ) )

Steps to reproduce the behavior:

Expected behavior

Be able to use a customized validation set, not the random split Tensorflow uses.