implicit-hyper-opt
implicit-hyper-opt copied to clipboard
Cannot set attribute `train_data` etc. of datasets
When executing the code as-is, pytorch throws an error when trying to subsample the datasets according to the command line parameter. The attribute needs to be changed from train_data
to data
, train_labels
to labels
, etc.
Fixed in https://github.com/ThrunGroup/implicit-hyper-opt/blob/master/data_loaders.py#L57-L58