Following up on my ‘Solved: Abalone Shell Load CSV batch input from dataset’ topic:
abalone_csv_ds = tf.data.experimental.make_csv_dataset( abalone_file_path, column_names=["Length", "Diameter", "Height", "Whole weight", "Shucked weight", "Viscera weight", "Shell weight", "Age"], batch_size=10, # Artificially small to make examples easier to show. label_name='Age', num_epochs=1, ignore_errors=True,) def pack(features, label): return tf.stack(list(features.values()), axis=-1), label packed_dataset = abalone_csv_ds.map(pack) Model.fit(packed_dataset, ..)
As make_csv_dataset does not seem to support split: I guess packed_dataset is not split automatically into a training and test set? Any suggestions on how to split the CSV batches into a train and validation set?