upgrading Accuracy layer: (1) efficient CPU implementation O(L) for top_k, no need for fancy priority_queue etc. (2) GPU implementation
S
Shai committed
62e0c8559045cb2b5a12e0d6c41acd25d4122630
Parent: fac7434
Committed by Shai <shaibagon@gmail.com>
on 10/10/2017, 5:30:36 PM