Synecdoche: Hypernetworks for Haiku in JAX
Project description
Synecdoche is a micro-library built on top of DeepMind's Haiku library that implements hypernetworks and other methods for compressed weight search and optimization.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
synecdoche-0.0.5.tar.gz
(4.9 kB
view hashes)
Built Distribution
Close
Hashes for synecdoche-0.0.5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 165d9788fd71643089b007769058ee0f7bff74ca7d9507675d094335a71ff9d6 |
|
MD5 | 85ffd3d9866bea9e0ad980909f90a35c |
|
BLAKE2b-256 | fe4e509b84b0bba587a72a5b5bd718228d2d64d5ebe9cf951bd8cdfcedf20f32 |