Open motiwari opened 2 years ago
Oh, the num_train
is used to split the train and validation set properly. Still don't know about the other questions
I suspect that the difference in train_data, train_labels and data, targets is due to a difference in random sampling for the different attributes. It is probably not material since both
I've discovered at least one cause of discrepancy between our master and Lorraine's: https://github.com/ThrunGroup/implicit-hyper-opt/blob/master/data_loaders.py#L75-L81
Somehow, when we changed
train_data
todata
andtrain_labels
totargets
, this results in different behavior.Additionally, it's not clear to me why
num_train
is used for the val set as wellI'm also not sure why changing those field names leads to different behavior