xianglinyang/TimeVis

Official source code for IJCAI 2022 Paper: Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training

26
/ 100
Experimental

This project helps machine learning researchers and practitioners understand how their deep learning models learn over time. It takes snapshots of a deep classifier model's state at different training epochs, along with the corresponding training and testing data. The output is a "time-travelling" visualization that reveals the evolution of the model's decision boundaries and data representations.

No commits in the last 6 months.

Use this if you need to visualize and analyze the training process of a deep classifier to understand why it makes certain predictions or how its internal representations change across epochs.

Not ideal if you are working with non-classification models, or if you need real-time monitoring of model training rather than a post-hoc analysis.

deep-learning-research model-interpretability neural-network-training machine-learning-visualization classifier-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Jupyter Notebook

License

Last pushed

May 06, 2024

Commits (30d)

0

Get this data via API

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

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