Look inside the workings of "Label Smoothing"
This blog post describes how and why does "trick" of label smoothing improves the model accuracy and when should we use it
deep-learning classification image-classification computer-vision label-smoothing tutorial
Objectives & Highlights

1. This blog posts aims at instilling an understanding of "Label Smoothing" in the minds of reader. 2. At the end of post, it is concluded that if your dataset has symantically similar classes or mislabelled images, label smoothing can improve your model accuracy. 3. This blog also explains a new way of thinking about increasing or decreasing of logits which was mentioned in the paper "When Does Label Smoothing work" by Rafael Müller et.al

Don't forget to tag @Abhimanyu08 in your comment.

Authors original post
Currently diving deep into both practical and theoretical aspects of deep learning.
Share this project
Similar projects
How to Train Your Neural Net
Deep learning for various tasks in the domains of Computer Vision, Natural Language Processing, Time Series Forecasting using PyTorch 1.0+.
Predicting mortgage approvals: EDA and Azure ML Studio
Introductory EDA (Exploratory Data Analysis) on mortgage approvals. Our goal is to explore and analyze the data then we design a predictor on Azure ML ...
Planar Data Classification
Planar Data Classification with one Hidden Layer , performed using traditional Mathematical approach.
Cross-entropy for Classification
Usages of cross-entropy for binary classification, multi-class classification, and multi-label classification.