TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'

[sd12832]

I am currently trying to run the program with Python3 on my Mac OSX. But as I run it with the .sh script, I do not seem to be getting any output. In order to investigate more, I used a simple:

python3 predict.py sample.flac

This gave me the set of errors below:

/usr/local/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Using TensorFlow backend.
Traceback (most recent call last):
  File "predict.py", line 131, in <module>
    model = InstrumentClassifier(args.model_dir)
  File "predict.py", line 47, in __init__
    self.model = load_model_from_dir(model_dir)
  File "predict.py", line 44, in load_model_from_dir
    model_dir + '/model_arch.yaml',
TypeError: unsupported operand type(s) for +: 'NoneType' and 'str'

Could you please guide me as to the proper procedure to fix this error?

[bzamecnik]

Hi Sharan, Thanks. Your model_id is not defined. Check the configuration for this parameter. Bohumir Dne 5. 3. 2018 18:00 napsal uživatel "Sharan Duggirala" < [email protected]>:

…

I am currently trying to run the program with Python3 on my Mac OSX. But as I run it with the .sh script, I do not seem to be getting any output. In order to investigate more, I used a simple: python3 predict.py sample.flac This gave me the set of errors below: /usr/local/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import register_converters as _register_converters Using TensorFlow backend. Traceback (most recent call last): File "predict.py", line 131, in <module> model = InstrumentClassifier(args.model_dir) File "predict.py", line 47, in __init__ self.model = load_model_from_dir(model_dir) File "predict.py", line 44, in load_model_from_dir model_dir + '/model_arch.yaml', TypeError: unsupported operand type(s) for +: 'NoneType' and 'str' Could you please guide me as to the proper procedure to fix this error? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#41>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AAbOrGSzMjBnIc4PInKFvkONazFyn4jXks5tbW8SgaJpZM4Sco4p> .

[sd12832]

Are you supposed to create a model? In that case, which function should I invoke?

[bzamecnik]

I think you can use a pretrained model at https://github.com/bzamecnik/deep-instrument-heroku/tree/master/static/model/2016-10-15_22-11-47_31fdbcbb. Or you train train yours. I hope the README is covering that well.

[bzamecnik]

Aah, I see the problem. model_dir CLI arg is required, but not marked as such. You should call:

python3 predict.py sample.flac -m path_to_model/

[sd12832]

Let me try running this. The README was a bit confusing, therefore, I went straight for the .sh wrapper. But since, it was not giving any errors, I went for the predict.py.

Could you detail how to train the model with your own data (I wanted to do this with the available files, but I keep facing various errors).

Are only .flacs accepted as of now?

[sd12832]

Hey, so I tried running this, and I got:

Traceback (most recent call last):
  File "predict.py", line 135, in <module>
    print(model.predict_class_label(args.audio_file))
  File "predict.py", line 98, in predict_class_label
    x_features = self.load_features(audio_file)
  File "predict.py", line 87, in load_features
    x_features = self.ch.transform(x)
AttributeError: 'dict' object has no attribute 'transform'

[sd12832]

Also, I wanted a few things cleared up. Should the entire process() follow this:

extract_features.py -> prepare_training_data.py -> train.py -> predict.py

I understand the inputs to extract_features.py. But what are the inputs into prepare_training_data.py? Could you detail this more?