farhad-dalirani/PytorchRevelio

Visualization toolkit for learned features of neural networks in PyTorch. Feature Visualizer, Saliency Map, Guided Gradients, Grad-CAM, DeepDream, ...

35
/ 100
Emerging

PytorchRevelio is a visualization toolkit that helps machine learning researchers and practitioners understand what their PyTorch neural networks have learned. It takes a pre-trained or custom PyTorch model and generates visual representations like feature maps and saliency maps, revealing how different parts of the network react to inputs. This helps users interpret the internal workings of their deep learning models, making them more transparent and debuggable.

No commits in the last 6 months.

Use this if you need to interpret why your PyTorch neural network makes certain decisions or to visualize the features it has learned from your data.

Not ideal if you are working with non-PyTorch deep learning models or if you need a high-level, production-ready monitoring dashboard for model performance.

deep-learning-interpretability neural-network-visualization model-debugging pytorch-analysis explainable-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

44

Forks

5

Language

Python

License

MIT

Last pushed

May 23, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/farhad-dalirani/PytorchRevelio"

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