-
Notifications
You must be signed in to change notification settings - Fork 130
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Output as *.mid file parameters for a generations of a chorale of length 100 #9
Comments
Default dataset is the Bach Chorales dataset obtained from music21 by corpus.getBachChorales function. For the moment, create the 'datasets/raw_dataset' folders in DeepBach folder. Calling the program should preprocess, pickle and save the Bach Chorales dataset at location BACH_DATASET Pickled datasets as well as pretrained models will be available soon |
I couldn't find the Bach Chorales dataset from music21. Do you have the links? |
Please see function music21.corpus.getBachChorales(fileExtensions='xml') |
Note that the pre-trained model and pre-processed dataset is already available for download: See the README. Get it from Dropbox manually or have it downloaded/extracted by a script:
Since pre-processing all the chorales from music21 takes about an hour this might be good for a quick start. |
Hi,
I tried the following command after installing all the dependencies and the DeepBach code:
python3 deepBach.py -l 100 -o deepBach.mid
Here is the error I get:
It seems that the dataset/raw_dataset/back_dataset.pickle is missing. Will you be providing that file in the future? If there is no file, it uses the constant BACH_DATASET instead and fails.
I checked out the
indexed_chorale_to_score
function fromdata_utils
library before this snippet of code above. The code for that function is the following:There is also a function that converts the score into midi that uses the output of the previous function for the score variable on line 55 of deepBach.py. Do I need to make any mods?
What should I do? Can you provide the pretrained dataset or a dataset of MIDIs?
The text was updated successfully, but these errors were encountered: