search

magenta / ddsp

DDSP: Differentiable Digital Signal Processing
https://magenta.tensorflow.org/ddsp
Apache License 2.0
2.92k stars 341 forks source link

'Autoencoder' object has no attribute 'get_audio_from_outputs' in colab/demos/timbre_transfer.ipynb #262

Closed jamesliu closed 4 years ago

jamesliu commented 4 years ago

I run timber_transfer.ipynb with the error below. Is it version issue? Thanks

AttributeError Traceback (most recent call last)

in () 7 outputs = model(af, training=False) 8 print(type(model)) ----> 9 audio_gen = model._outputs(outputs) 10 print('Prediction took %.1f seconds' % (time.time() - start_time)) AttributeError: 'Autoencoder' object has no attribute 'get_audio_from_outputs'
jesseengel commented 4 years ago

Hi,

Yah, I'm not sure when you tried the demo, but it should work fine now as the version has been corrected.

On Wed, Nov 11, 2020 at 7:29 PM James notifications@github.com wrote:

I run timber_transfer.ipynb with the error below. Is it version issue?

AttributeError Traceback (most recent call last) in () 7 outputs = model(af, training=False) 8 print(type(model)) ----> 9 audio_gen = model._outputs(outputs) 10 print('Prediction took %.1f seconds' % (time.time() - start_time))

AttributeError: 'Autoencoder' object has no attribute 'get_audio_from_outputs'

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/magenta/ddsp/issues/262, or unsubscribe https://github.com/notifications/unsubscribe-auth/AANFCCNBTT3AGX3A4TXQ6ELSPNJDFANCNFSM4TSYCH5Q .

jamesliu commented 4 years ago

@jesseengel After updating ddsp, it is fixed. Thanks.