sfaira.estimators.EstimatorKerasEmbedding.evaluate¶
- EstimatorKerasEmbedding.evaluate(batch_size: int = 128, max_steps: int = inf)¶
Evaluate the custom model on test data.
Defaults to run on full data if idx_test was not set before, ie. train() has not been called before.
- Parameters
batch_size – Batch size for evaluation.
max_steps – Maximum steps before evaluation round is considered complete.
- Returns
Dictionary of metric names and values.