Fixed UnknownError exception by changing how GRU is implemented in the model

[TassaraR]

This changes refer to the sequential recommendations example notebook.

Original published code threw the following exception while trying to train the model (in Google Collab)

query_model = tf.keras.Sequential([
    tf.keras.layers.StringLookup(
      vocabulary=unique_movie_ids, mask_token=None),
    tf.keras.layers.Embedding(len(unique_movie_ids) + 1, embedding_dimension), 
    tf.keras.layers.GRU(embedding_dimension)
])

model.fit(cached_train, epochs=3)

Epoch 1/3
---------------------------------------------------------------------------
UnknownError                              Traceback (most recent call last)
[<ipython-input-87-5f54841df216>](https://localhost:8080/#) in <module>
----> 1 model.fit(cached_train, epochs=3)

1 frames
[/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py](https://localhost:8080/#) in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     53     ctx.ensure_initialized()
     54     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55                                         inputs, attrs, num_outputs)
     56   except core._NotOkStatusException as e:
     57     if name is not None:

UnknownError: Graph execution error:

Fail to find the dnn implementation.
	 [[{{node CudnnRNN}}]]
	 [[sequential_18/gru_8/PartitionedCall]] [Op:__inference_train_function_26280]

Changing

tf.keras.layers.GRU(embedding_dimension)

to

tf.keras.layers.RNN(tf.keras.layers.GRUCell(embedding_dimension))

Fixed this issue and allowed the model to be trained normally

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB