ZF/FERPlus
1
0
Fork 0
mirror of https://gitcode.com/gh_mirrors/fe/FERPlus.git synced 2025-12-30 05:22:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Cha Zhang
2016-09-16 07:23:43 -07:00
committed by GitHub
parent eb57565c75
commit e4efb4f8cd
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -1,7 +1,7 @@
# FER+
This is new label for Emotion FER dataset, each image is tagged by 10 taggers, which provide better quality ground truth for still image emotion than the original FER label. Have 10 taggers for each image enable us to create an emotion probability distribution per face so that we can learn a probability or multi-label instead of the conventional majority voting, as described in: https://arxiv.org/abs/1608.01041
This is new label for Emotion FER dataset. Each image is tagged by 10 crowd-sourced taggers, which provide better quality ground truth for still image emotion than the original FER label. Having 10 taggers for each image enables us to create an emotion probability distribution per face so that we can learn a probability or multi-label instead of the conventional majority voting, as described in: https://arxiv.org/abs/1608.01041
The new label file is named: fer2013new.csv, it contains the same number of rows as the original fer2013.csv label file with the same order. So that you infer which emotion tag belong to which image, because we can't host the actual image content. Here the original FER label: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
The new label file is named: fer2013new.csv, it contains the same number of rows as the original fer2013.csv label file with the same order, so that you infer which emotion tag belong to which image. Since we can't host the actual image content, please find the original FER data set here: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
We also provide a simple parsing code in python to demonstrate how to parse the new label and how to convert it to probability distribution (there is multiple way to do it, we show an example). The parsing code is in src/ReadFERPlus.py