Tweeted By @karpathy

`numpy.split(ary, indices_or_sections, axis=0)` vs. `torch.split(tensor, split_size_or_sections, dim=0)`; indices or sizes for each chunk, fight! (more seriously though still finding it hard to keep track of which var is tensor/array and remembering the random api differences 🧐)

— Andrej Karpathy (@karpathy) November 6, 2019