Open dimstudio opened 3 years ago
Hey @dimstudio, Do you mean
To 1.:
if need_train_test_folder(dataset, ignore_files):
data_helper.create_train_test_folders(data=dataset,
new_folder_location=None,
train_test_ratio=0.85,
ignore_files=ignore_files,
to_exclude=to_exclude
)
To 2.: I am not so sure anymore. I think we adapted the code to use CSVs because for Mobius it was not feasible anymore. If I remember correctly I wanted to create a branch with the current code from the timepoint where we submitted the CPR tutor paper. It is still possible to check that out via GitHub and create it afterwards, but the code probably has changed a lot. For this you can go through the commit history and check out an earlier version.
I meant the 2nd, how to directly train using the MLT-files. I have a new dataset in MLT. What do you suggest to do? convert first in CSV?
That would be best, yes.
Dear @HansBambel, I am trying to use the library to train a model with the MLT-JSON data format (similar to the CPR Tutor). How can I change the current load of CSV files into MLT-JSON? Thanks