hkproj/quantization-notes
Notes on quantization in neural networks
These notes and sample code provide a practical guide to optimizing neural networks for efficiency. You'll learn how to take a standard neural network model and reduce its computational footprint, making it faster and consume less memory. This is for machine learning practitioners, researchers, and engineers who deploy models on resource-constrained hardware or seek to speed up inference.
121 stars. No commits in the last 6 months.
Use this if you need to make your deep learning models run faster or use less memory, especially for deployment on edge devices or in high-throughput applications.
Not ideal if you are looking for a conceptual introduction to neural networks or deep learning architectures, as it focuses specifically on optimization techniques.
Stars
121
Forks
24
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hkproj/quantization-notes"
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...