---
title: "Discussion on \"My Baseline Broke: What an 18% Accuracy Gap Taught Me About Deep Learning\" | Hashnode"
description: "Discussion on \"My Baseline Broke: What an 18% Accuracy Gap Taught Me About Deep Learning\". Recently, I set out to reproduce a standard CNN baseline on CIFAR-10.\nIt was supposed to be a warm-up. A \"hello world\" for my semester project. I wrote the code, grabbed the dataset, and queued up fou"
url: "https://hashnode.com/posts/my-baseline-broke-what-an-18-accuracy-gap-taught-me-about-deep-learning/69f1f1ac6e0124c05ef5d838"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [My Baseline Broke: What an 18% Accuracy Gap Taught Me About Deep Learning](https://d1shasaini.hashnode.dev/my-baseline-broke-what-an-18-accuracy-gap-taught-me-about-deep-learning?utm_source=hashnode&utm_medium=feed)

Recently, I set out to reproduce a standard CNN baseline on CIFAR-10. It was supposed to be a warm-up. A "hello world" for my semester project. I wrote the code, grabbed the dataset, and queued up fou

Apr 29 · 6 min read · d1shasaini.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)
-   [#machine-learning](https://hashnode.com/tag/machine-learning)

## Written by

[disha](https://hashnode.com/@d1shaa)

@d1shaa

  
[View profile](https://hashnode.com/@d1shaa)

## Responses

Markdown supported · ⌘↵ to post

No responses yet.