google-research/morph-net

Fast & Simple Resource-Constrained Learning of Deep Network Structure

58
/ 100
Established

This helps deep learning practitioners optimize their neural networks to be smaller, faster, or use less memory without significantly impacting accuracy. You provide an existing convolutional neural network and a target, like reducing FLOPs or model size. The system outputs a modified network architecture that meets your resource constraints. It's for anyone deploying deep learning models in environments with strict computational or memory limits.

1,033 stars.

Use this if you have an existing deep neural network that is too large or slow for your deployment environment and you need to reduce its resource consumption.

Not ideal if you are looking to change the fundamental layer topology of your neural network or explore entirely new architectures from scratch.

deep-learning-deployment model-optimization resource-constrained-ai computer-vision neural-network-pruning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,033

Forks

152

Language

Python

License

Apache-2.0

Last pushed

Feb 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-research/morph-net"

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