hub / github.com/HA-Transformer/MAT / AdaptiveSoftmax

Class AdaptiveSoftmax

fairseq/modules/adaptive_softmax.py:50–206 · view source on GitHub ↗

This is an implementation of the efficient softmax approximation for graphical processing units (GPU), described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309).

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 5

__init__Method · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected