Open zhutmost opened 4 years ago
When using the random_split function provided in PyTorch to split the dataset to training and validation sets, the propotion of categories are imbalanced.
random_split
Fixed in commit https://github.com/zhutmost/lsq-net/commit/02f802e6652d3d067b953f756f01dd2d50d54456.
However, the imbalance among categories still exists. Maybe need another Sampler.
Sampler
When using the
random_split
function provided in PyTorch to split the dataset to training and validation sets, the propotion of categories are imbalanced.