jack-willturner/deep-compression
Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626
When deploying deep learning models, this project helps reduce the model's size and computational requirements. It takes an existing neural network, such as a ResNet, and optimizes it to use fewer parameters and connections without significantly losing accuracy. Data scientists and machine learning engineers working on edge devices or resource-constrained environments would find this useful.
181 stars. No commits in the last 6 months.
Use this if you need to deploy large neural networks to environments with limited memory or processing power, such as mobile phones, embedded systems, or IoT devices.
Not ideal if your primary concern is developing new model architectures from scratch, as this tool focuses on optimizing existing ones.
Stars
181
Forks
39
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jack-willturner/deep-compression"
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
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...