Minor updates

README.md

@@ -1,4 +1,4 @@
-## Release of Human-Rights-Archive-CNNs
+## Release of Human-Rights-Archive-CNNs [![Tweet](https://img.shields.io/twitter/url/http/shields.io.svg?style=social)](https://twitter.com/intent/tweet?text=The%20Human-Rights-Archive-CNNs%20for%20Human%20Rights%20Violations%20Recognition&url=https://github.com/GKalliatakis/Human-Rights-Archive-CNNs&hashtags=ML,DeepLearning,CNNs,HumanRights,HumanRightsViolations)
 
 We release various convolutional neural networks (CNNs) trained on _Human Rights Archive (HRA)_ to the public.
 HRA is the first verified-by-experts repository of human rights violations photographs, labelled with human rights semantic categories,
@@ -150,7 +150,8 @@ Please cite the following [paper](https://arxiv.org/pdf/1805.04714.pdf) if you u
 
 Please email [Grigorios Kalliatakis](mailto:[email protected]) if you have any questions or comments.
 
-
+<!---
 ### To-Do (after acceptance)
 
-- [ ] Update all weights files for Human-Rights-Archive-CNNs (currently are saved @ https://github.com/GKalliatakis/crispy-enigma)
+- [ ] Update all weights files for Human-Rights-Archive-CNNs (currently are saved @ https://github.com/GKalliatakis/crispy-enigma)
+-->

web_app_v1.2/templates/index.html

@@ -23,7 +23,8 @@ <h1>Human Rights Violations Recognition Demo using <span>Convolutional Neural Ne
                     high-level neural networks API and our fine-tuned Human-Rights-Archive-CNNs.
                     Please note that we are limited to the 8 classes (<i>arms, child labour, child marriage, detention centres,
                     disability rights, displaced populations, environment </i> and <i> out of school</i>)
-                    of Human Rights Archive (HRA) dataset &#38; an extra class of <i> &#8216;no violation&#8217;</i> which is currently being used for this demo.
+                    of Human Rights Archive (HRA) dataset &#38; an extra class of <i> &#8216;no violation&#8217;</i> which is
+                    currently being used for this demo.
                     Keep in mind that this is image classification and not object detection,
                     so the network is forced to output a single class through softmax.
                     Best results are on images where the classification target spans a large portion of the image.</p>