From 35ddc4873d8ea2fad093692a0b51ffd0d045997f Mon Sep 17 00:00:00 2001 From: Harald Scheidl <harald_scheidl@hotmail.com> Date: Sat, 5 Jan 2019 16:54:17 +0100 Subject: [PATCH] link to article about analyzing tool --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index cfd29f1..c7f0726 100644 --- a/README.md +++ b/README.md @@ -172,6 +172,7 @@ Draw a dot above the "a" (red region in plot) and you will get "aive" instead of The second plot (right) shows how the probability of the ground-truth text changes when the text is shifted to the right. As can be seen, the model is not translation invariant, as all training images from IAM are left-aligned. Adding data augmentation which uses random text-alignments can improve the translation invariance of the model. +More information can be found in [this article](https://towardsdatascience.com/6c04864b8a98).  -- GitLab