Error in model save , homework week3 C4W3

Course Q&A TensorFlow Developer Professional Sequences, Time Series and Prediction
1

hello i get the following error when i run my model save

AttributeError Traceback (most recent call last)
in
1 # Save your model in the SavedModel format
----> 2 model.save(‘saved_model/my_model’)
3
4 # Compress the directory using tar
5 get_ipython().system(’ tar -czvf saved_model.tar.gz saved_model/')

/opt/conda/lib/python3.8/site-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.traceback)
—> 67 raise e.with_traceback(filtered_tb) from None
68 finally:
69 del filtered_tb

/opt/conda/lib/python3.8/site-packages/keras/layers/core/lambda_layer.py in _serialize_function_to_config(self, inputs, allow_raw)
279 module = inputs.module
280 elif callable(inputs):
→ 281 output = inputs.name
282 output_type = ‘function’
283 module = inputs.module

AttributeError: ‘Lambda’ object has no attribute ‘name’

t

2

Please click my name and message your notebook as an attachment.

3

The error you are observing is due to the last layer in your model. There’s no need to use a lambda layer inside another lambda layer like tf.keras.layers.Lambda(tf.keras.layers.Lambda(...)). It’s sufficient to have a single lambda layer to perform the computation.