return info dicts for specified keys (or all if None) at specified indices (or out_indices if None)

Returns all the subsets of this set. This is a generator.

Compute relative logits along one dimension As per: https://gist.github.com/aravindsrinivas/56359b79f0ce4449bcb04ab4b56a57a2 Originally from

Compute relative logits along one dimension As per: https://gist.github.com/aravindsrinivas/56359b79f0ce4449bcb04ab4b56a57a2 Originally from

Selective Kernel Convolution Module As described in Selective Kernel Networks (https://arxiv.org/abs/1903.06586) with some modifications.

NOTE: shape arg should include spatial dim only

DropBlock. See https://arxiv.org/pdf/1810.12890.pdf DropBlock with an experimental gaussian noise option. This layer has been tested on a few tr

DropBlock. See https://arxiv.org/pdf/1810.12890.pdf DropBlock with an experimental gaussian noise option. Simplied from above without concern fo

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Returns the location of the directory where models are cached (and creates it if necessary).