lucaslie/torchprune
A research library for pytorch-based neural network pruning, compression, and more.
This is a research library for PyTorch-based neural network pruning. It helps machine learning researchers and practitioners make their deep learning models smaller and faster. You input your existing PyTorch neural network, and it outputs a compressed version of that network, often with minimal loss in performance. This is for machine learning engineers, AI researchers, and data scientists working with deep learning models.
163 stars. No commits in the last 6 months.
Use this if you need to reduce the computational cost or memory footprint of your PyTorch neural networks for deployment or efficiency, and want to explore various pruning techniques.
Not ideal if you are looking for a high-level, automated pruning solution without needing to understand different algorithms or manage experimental configurations.
Stars
163
Forks
24
Language
Shell
License
MIT
Category
Last pushed
Nov 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lucaslie/torchprune"
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...