From f8acbcc7a0a2134dc55467b314356407cf80b407 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=BB=8E=E5=BC=BA?= Date: Sat, 10 Jun 2017 13:52:38 +0800 Subject: [PATCH 1/4] Create README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 7191f0c..edb0c3c 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@ # relation-network -implement relation network introduced by deepmind using keras. +keras implementation of [A simple neural network module for relational reasoning](https://arxiv.org/pdf/1706.01427.pdf) 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. 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 2/4] 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%). From 9170da8381b198e795e3cc7922472df6bf6f7f17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=BB=8E=E5=BC=BA?= Date: Sat, 10 Jun 2017 20:16:27 +0800 Subject: [PATCH 3/4] Create README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 78c702c..ef301fe 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ -# relation-network +89# relation-network keras implementation of [A simple neural network module for relational reasoning](https://arxiv.org/pdf/1706.01427.pdf) 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 98.10%, 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 89.10%, which is much higher than the previous state of the art (61.99%). From 235b1d31e46c8ceafaba5904c64324447faaae5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=BB=8E=E5=BC=BA?= Date: Sat, 10 Jun 2017 20:17:33 +0800 Subject: [PATCH 4/4] Create README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ef301fe..fc583f4 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -89# relation-network +# relation-network keras implementation of [A simple neural network module for relational reasoning](https://arxiv.org/pdf/1706.01427.pdf) 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.