A collection of common functionality to simplify the design, training and evaluation of machine learning models based on pytorch with an emphasis on speech processing.
Now that the maybe_add function disappeared from the data preparation, can you add an example_to_device method to the model that only transfers to the GPU those keys from the example that are required for training? You can use pt.data.batch.example_to_device for that
Now that the
maybe_add
function disappeared from the data preparation, can you add anexample_to_device
method to the model that only transfers to the GPU those keys from the example that are required for training? You can usept.data.batch.example_to_device
for that