Home Projects dropblock
dropblock
Python

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

by miguelvr · GitHub
Stars
Forks
License
Created
Last commit
Language
computer-visionconvolutional-neural-networksdropblockMITPython
View on GitHub
In plain words

Apply a new regularization technique to improve the performance of convolutional neural networks in PyTorch.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
dropblock — GitHub preview card
📈 Star history
595594
2026-07-202026-08-31
📈 Track dropblock

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

dropblock has 594 stars on GitHub. It has been forked 95 times. dropblock is written mainly in Python. It has been in active development since 2018. dropblock is available under the MIT license. Its main topics are computer-vision, convolutional-neural-networks, dropblock, dropout.

Frequently asked questions

What is dropblock?

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

Is dropblock open source?

dropblock is an open-source project. It is released under the MIT license.

Is dropblock free?

Yes. dropblock is free and open source — you can use, modify and self-host it.

What license does dropblock use?

dropblock is available under the MIT license.

What language is dropblock written in?

dropblock is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — dropblock

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=miguelvr-dropblock)](https://olud.ai/project/miguelvr-dropblock.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.