provide a sample case

[terry07]

Could you setup a quick demo? I cannot understand why any input file to be theorized as a new class and i am getting error on train.py: 'ValueError: Cannot feed value of shape (1, 2) for Tensor u'Placeholder_1:0', which has shape '(?, 4)'

[fredlemieux]

I concurr, the documentation is a little sparse, I would also really like to know exactly how to train sound-cnn with my own audio. Thanks

[JoelDeLeon]

Same here.