Shikha-code36/early-exit-cnn

A deep learning framework that implements Early Exit strategies in Convolutional Neural Networks (CNNs) using Deep Q-Learning (DQN). This project enhances computational efficiency by dynamically determining the optimal exit point in a neural network for image classification tasks on CIFAR-10.

20
/ 100
Experimental

This project offers a specialized deep learning framework for image classification that intelligently decides how much processing an image needs. It takes in images and outputs their classification along with how early the decision was made, saving computational resources. This tool is designed for machine learning engineers or researchers working with computer vision models, especially those concerned with deploying efficient image classification systems.

No commits in the last 6 months.

Use this if you need to classify images quickly and efficiently, optimizing for both speed and accuracy in environments where computational resources are a concern.

Not ideal if you are looking for a simple, out-of-the-box image classifier without needing to customize or understand the underlying deep learning and reinforcement learning mechanics.

image-classification computational-efficiency deep-learning-deployment computer-vision resource-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Shikha-code36/early-exit-cnn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.