A toolkit for subnetwork analysis
Project description
NeuroSurgeon
NeuroSurgeon is a python toolkit built to enable deep learning researchers to easily uncover and manipulate subnetworks within trained models. NeuroSurgeon provides a simple API to inject differentiable binary masks techniques into linear, attention, and convolution layers in BERT, GPT, ResNet, and ViT-style models within Huggingface Transformers. Differentiable masking has a variety of use cases for deep learning research, such as:
- Pruning to uncover functional subnetworks
- Relevant Papers:
- Subnetwork Probing
- Relevant Papers:
- Training with L0 Regularization
- Relevant Papers:
Documentation
Read the NeuroSurgeon Documentation
Tutorial
To get started with NeuroSurgeon, check out the tutorial here. This covers the basic workflow for using NeuroSurgeon to uncover functional subnetworks within a trained model.
Install
NeuroSurgeon requires python 3.9 or higher and several libraries, including Transformers and PyTorch. Installation can be done using PyPi:
pip install NeuroSurgeon
Logo Prompt
NeuroSurgeon's logo was created with the help of DALL-E 2, using the prompt "A cute cartoon robot doctor smiling with a stethoscope".
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for NeuroSurgeon-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 35be350037117ed388ea62745079b3e137527a74b26015486ab37f2d9fce53af |
|
MD5 | f4e7a68fbe81e3453abaa3efe2dc8d42 |
|
BLAKE2b-256 | 6d347021388eaef7397ba24065632aa21fc46f41c6511a62452a63e039914cc1 |