StijnVerdenius/SNIP-it
This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural networks. Amongst others it implements structured pruning before training, its actual parameter shrinking and unstructured before/during training.
This project helps machine learning engineers and researchers optimize deep learning models by reducing their size and computational demands. It takes an existing neural network and a dataset, then applies various pruning algorithms to produce a smaller, more efficient model that retains high accuracy. This is ideal for anyone working with neural networks who needs to deploy models to resource-constrained environments or accelerate training and inference.
No commits in the last 6 months.
Use this if you need to compress large deep learning models for faster inference, reduced memory footprint, or deployment on devices with limited computational resources.
Not ideal if your primary goal is to improve model accuracy rather than efficiency, or if you're not working with deep learning neural networks.
Stars
32
Forks
4
Language
Python
License
MIT
Category
Last pushed
May 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/StijnVerdenius/SNIP-it"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...