Custom Object Detection TFLite model error (pascal voc) - ValueError:

ValueError: The size of the train_data (0) couldn't be smaller than batch_size (4). To solve this problem, set the batch_size smaller or increase the size of the train_data.

train_data = object_detector.DataLoader.from_pascal_voc(
'/home/pi/kastze2/train',
'/home/pi/kastze2/train',
['cat', 'mouse', 'cat+mouse']

)

val_data = object_detector.DataLoader.from_pascal_voc(
    '/home/pi/kastze2/validate',
    '/home/pi/kastze2/validate',
    ['cat', 'mouse', 'cat+mouse']
)

model = object_detector.create(train_data, model_spec=spec, batch_size=4, train_whole_model=True, epochs=20, validation_data=val_data)