Can someone guide, how to include the Custom DataGenerator functionality from tf.keras with methods
keras.utils.Sequence ,
on_epoch_end, __len__, __getitem__ ,
`
in tensorflow alone?
Can someone guide, how to include the Custom DataGenerator functionality from tf.keras with methods
keras.utils.Sequence ,
on_epoch_end, __len__, __getitem__ ,
`
in tensorflow alone?
I don’t understand your issue, do you have a minimized standalone example or Colab?
Yes, here is the link. Uses custom generator based on
keras.utils.Sequence
and some add-ons to fetch the cores.
Is there way to implement in native TensorFlow alone (no Keras)?
it is just really like a plain python class. Please check yourself the source code at: