Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
% Fixed extra right bracket | |
% | |
% Evgenii Zheltonozhskii, 09/28/2020, zheltonozhskiy@gmail.com | |
% | |
% --------------------------------------------------------------- | |
% Modified CVPR ieee_fullname.bst to support natbib | |
% | |
% Evgenii Zheltonozhskii, 03/10/2019, zheltonozhskiy@gmail.com | |
% | |
% --------------------------------------------------------------- |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def top_k_top_p_filtering(logits, top_k=0, top_p=0.0, filter_value=-float('Inf')): | |
""" Filter a distribution of logits using top-k and/or nucleus (top-p) filtering | |
Args: | |
logits: logits distribution shape (vocabulary size) | |
top_k >0: keep only top k tokens with highest probability (top-k filtering). | |
top_p >0.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering). | |
Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751) | |
""" | |
assert logits.dim() == 1 # batch size 1 for now - could be updated for more but the code would be less clear | |
top_k = min(top_k, logits.size(-1)) # Safety check |