From d339f972d22300e9391f5c96e9764d79a3a3ad20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=BB=8E=E5=BC=BA?= Date: Sat, 10 Jun 2017 20:15:04 +0800 Subject: [PATCH] Create README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index edb0c3c..78c702c 100644 --- a/README.md +++ b/README.md @@ -3,5 +3,5 @@ keras implementation of [A simple neural network module for relational reasonin Relation network is a noval neural network introduced by deepmind in [A simple neural network module for relational reasoning](https://arxiv.org/pdf/1706.01427.pdf). It can achieve super-human performance in challenging visual question answering datasets such as CLEVR. -I implement Relation network using keras and train it on a challenging visual question answering dataset called [Cornell NLVR](https://github.com/cornell-lic/nlvr). The training is in progress. The temporal test accuracy is 76.87%, which is much higher than the previous state of the art (61.99%). +I implement Relation network using keras and train it on a challenging visual question answering dataset called [Cornell NLVR](https://github.com/cornell-lic/nlvr). The training is in progress. The temporal test accuracy is 98.10%, which is much higher than the previous state of the art (61.99%).