Closed michiyosony closed 7 years ago
I found that running prepare.py was correctly splitting up the training set and the validation set. This was caused by the number of samples (obtained from the command line arguments) being a string instead of a number.
prepare.py
I found that running
prepare.py
was correctly splitting up the training set and the validation set. This was caused by the number of samples (obtained from the command line arguments) being a string instead of a number.