wassname/relation-network
1
0
Fork 0
mirror of https://github.com/wassname/relation-network.git synced 2026-09-09 11:33:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Create README.md

Browse Source
This commit is contained in:
黎强
2017-06-10 20:16:27 +08:00
committed by GitHub
parent d339f972d2
commit 9170da8381
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -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%).