ModelZoos/ModelZooDataset

Model Zoos published at the NeurIPS 2022 Dataset & Benchmark track: "Model Zoos: A Dataset of Diverse Populations of Neural Network Models"

21
/ 100
Experimental

This dataset offers curated collections of trained neural network models, called "model zoos," capturing how models evolve during training. You get raw model checkpoints, their performance metrics over time (like accuracy), and their internal weights and biases. This is for researchers and machine learning engineers who want to deeply analyze the behavior and characteristics of neural network populations.

No commits in the last 6 months.

Use this if you are researching the fundamental properties of neural networks, such as how model weights change during training or how model populations relate to each other.

Not ideal if you are looking for ready-to-use, single best-performing models for immediate deployment in a production system.

neural-network-research machine-learning-engineering model-analysis deep-learning-dynamics model-sparsification
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

59

Forks

1

Language

Python

License

Category

model-zoos

Last pushed

Oct 02, 2025

Commits (30d)

0

Get this data via API

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

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