FrancescoSaverioZuppichini/BottleNeck-InvertedResidual-FusedMBConv-in-PyTorch

A little walk-trough different types of the block with their corresponding implementation in PyTorch

33
/ 100
Emerging

This project helps deep learning practitioners understand and implement various convolutional neural network (CNN) building blocks, like Residual, Bottleneck, and Inverted Residual connections, that are fundamental to architectures such as ResNet, MobileNet, and EfficientNet. It provides clear explanations and direct PyTorch code examples for these blocks, taking input tensors and outputting processed tensors according to the block's design. This is for machine learning engineers or researchers working on computer vision tasks.

No commits in the last 6 months.

Use this if you need to understand and implement advanced CNN building blocks in PyTorch for creating or modifying image recognition models.

Not ideal if you are looking for a high-level library to build complete deep learning models without needing to delve into the specifics of block implementations.

deep-learning computer-vision neural-network-architecture pytorch-development image-recognition
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

42

Forks

9

Language

Jupyter Notebook

License

Last pushed

Oct 14, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FrancescoSaverioZuppichini/BottleNeck-InvertedResidual-FusedMBConv-in-PyTorch"

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