diff options
author | skaae <skaaesonderby@gmail.com> | 2015-11-14 01:33:35 +0300 |
---|---|---|
committer | skaae <skaaesonderby@gmail.com> | 2015-11-14 01:33:35 +0300 |
commit | 894b13f16b69eadb7b8134d17008bcf9de04e2dc (patch) | |
tree | 9451972c4de3f83b209efc6ac810947fdb4cd7f2 | |
parent | c6e2b2a6c83e714a2d9f832995eb6d266075e0a6 (diff) |
spelling error v2
-rw-r--r-- | blog/_posts/2015-11-13-gan.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/blog/_posts/2015-11-13-gan.md b/blog/_posts/2015-11-13-gan.md index fc13583..4ee6588 100644 --- a/blog/_posts/2015-11-13-gan.md +++ b/blog/_posts/2015-11-13-gan.md @@ -147,8 +147,8 @@ A few other tricks are necessary for successful GAN training: ### Generating faces -We train our GAN using aligned and cropped images from the [Labeled faces in the wild](http://vis-www.cs.umass.edu/lfw/) dataset. After a around 5 epochs (around 30 minutes on a GPU) you should start to see some spooky faces (left). -Which after 100 epochs will look more pleasant (right). +We train our GAN using aligned and cropped images from the [Labeled faces in the wild](http://vis-www.cs.umass.edu/lfw/) dataset. After at around 5 epochs (around 30 minutes on a GPU) you should start to see some spooky faces (left). +And after 100 epochs will look more pleasant (right). <p align='center'><img width="80%" src="https://raw.githubusercontent.com/torch/torch.github.io/master/blog/_posts/images/samples_during_training.png"></p> |