From a284a7da8d1facbf984a22302665a2a50295a687 Mon Sep 17 00:00:00 2001 From: AlexeyAB <alexeyab84@gmail.com> Date: Wed, 08 Aug 2018 16:08:58 +0000 Subject: [PATCH] Try to use avx_hs() - slow and requires alignment 4096 bits < (l.size*l.size*l.c) May be faster only from 8192 bits and more. --- cfg/vgg-conv.cfg | 1 - 1 files changed, 0 insertions(+), 1 deletions(-) diff --git a/cfg/vgg-conv.cfg b/cfg/vgg-conv.cfg index ab0fb1e..21e1d72 100644 --- a/cfg/vgg-conv.cfg +++ b/cfg/vgg-conv.cfg @@ -6,7 +6,6 @@ channels=3 learning_rate=0.00001 momentum=0.9 -seen=0 decay=0.0005 [convolutional] -- Gitblit v1.10.0