diff options
author | Soumith Chintala <soumith@gmail.com> | 2015-09-22 18:07:19 +0300 |
---|---|---|
committer | Soumith Chintala <soumith@gmail.com> | 2015-09-22 18:07:19 +0300 |
commit | 478d07428e0e69303ac7d2dc656720b164ffddda (patch) | |
tree | d36e59303ba580e4784390bc33ba6eba1948ea38 /blog | |
parent | 0590bf079d8f13d37dd4a0348dd0be99e1453311 (diff) |
fixes
Diffstat (limited to 'blog')
-rw-r--r-- | blog/_posts/2015-09-21-rmva.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/blog/_posts/2015-09-21-rmva.md b/blog/_posts/2015-09-21-rmva.md index 7da6f3b..c3b590b 100644 --- a/blog/_posts/2015-09-21-rmva.md +++ b/blog/_posts/2015-09-21-rmva.md @@ -16,7 +16,7 @@ modular code available in the process. You can reproduce the RAM on the MNIST dataset using this [training script](https://github.com/Element-Research/rnn/blob/master/examples/recurrent-visual-attention.lua). We will use snippets of that script throughout this post. -You can then evaluate your trained models using the [evaluation script](https://github.com/Element-Research/rnn/blob/master/scripts/evaluate-rva.lua. +You can then evaluate your trained models using the [evaluation script](https://github.com/Element-Research/rnn/blob/master/scripts/evaluate-rva.lua). The paper describes a RAM that can be applied to image classification datasets. The model is designed in such a way that it has a bandwidth limited sensor of the input image. |