search

OMR-Research / tf-end-to-end

TensorFlow code to perform end-to-end Optical Music Recognition on monophonic scores through Convolutional Recurrent Neural Networks and CTC-based training.
MIT License
136 stars 58 forks source link

About Training Dataset #5

Closed thuhuwei closed 5 years ago

thuhuwei commented 5 years ago

Thanks for this work. And which dataset is employed to train two provided models, the original PrIMuS or Camera PrIMuS ?

calvozaragoza commented 5 years ago

The provided models were trained with PrIMuS, but the scripts can be executed for training with Camera-PrIMuS.

thuhuwei commented 5 years ago

Thanks. Another question: Do you consider to support multiple-voice polyphonic staves in near future?

calvozaragoza commented 5 years ago

Of course, that's an ongoing line of research but I don't know when I might get some results.