MarcoParola/pytorch-sidu
SIDU: SImilarity Difference and Uniqueness method for explainable AI
When working with image classification models, it can be challenging to understand why a model makes a particular decision. This tool helps you visualize which parts of an image are most important for a model's prediction, generating 'saliency maps' from your input images and a pre-trained PyTorch model. It's designed for machine learning engineers and researchers who need to interpret the behavior of their vision models.
No commits in the last 6 months. Available on PyPI.
Use this if you need to understand and explain the specific regions of an image that influence a pre-trained PyTorch classification model's output.
Not ideal if you are looking for an explainable AI method for non-image data types or models not built with PyTorch.
Stars
46
Forks
—
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 28, 2024
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MarcoParola/pytorch-sidu"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sp-nitech/diffsptk
A differentiable version of SPTK
trigeorgis/mdm
A TensorFlow implementation of the Mnemonic Descent Method.
clovaai/mxfont
Official PyTorch implementation of MX-Font (Multiple Heads are Better than One: Few-shot Font...
clovaai/fewshot-font-generation
The unified repository for few-shot font generation methods. This repository includes FUNIT...
Michedev/DDPMs-Pytorch
Implementation of various DDPM papers to understand how they work