From cd11d77dd0d71ab70949ab1d81a480572cafb587 Mon Sep 17 00:00:00 2001 From: Neal Wu Date: Fri, 16 Jun 2017 13:32:49 -0700 Subject: [PATCH] Remove the erroneous comment from resnet_v2.py again --- slim/nets/resnet_v2.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/slim/nets/resnet_v2.py b/slim/nets/resnet_v2.py index e8e7983452..f5af103342 100644 --- a/slim/nets/resnet_v2.py +++ b/slim/nets/resnet_v2.py @@ -25,8 +25,6 @@ The key difference of the full preactivation 'v2' variant compared to the 'v1' variant in [1] is the use of batch normalization before every weight layer. -Another difference is that 'v2' ResNets do not include an activation function in -the main pathway. Also see [2; Fig. 4e]. Typical use: