antoinebrl/torchextractor

Feature extraction made simple with torchextractor

41
/ 100
Emerging

This tool helps machine learning engineers and researchers easily access the internal calculations (features) from pre-trained neural networks like ResNet. You provide your existing neural network model and specify which internal layers you're interested in, and it gives you those specific feature outputs. This is for anyone who needs to inspect or reuse parts of a deep learning model without modifying its original code.

101 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to extract intermediate feature maps from a PyTorch model to use them for custom tasks like adding new layers, applying extra losses, or analyzing model behavior.

Not ideal if you are working with TorchScript compiled models, as this tool currently does not support them.

deep-learning-research model-analysis computer-vision feature-engineering pytorch-development
Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 7 / 25

How are scores calculated?

Stars

101

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2021

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/antoinebrl/torchextractor"

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