approx-ml/approx
Automatic quantization library
This tool helps machine learning engineers and researchers optimize their trained deep learning models. It takes an existing, trained neural network model and automatically reduces its size and computational requirements. The output is a more efficient, 'quantized' version of the original model that can run faster and with less memory, ideal for deployment on resource-constrained devices or for improving inference speed.
No commits in the last 6 months.
Use this if you need to deploy a trained machine learning model on hardware with limited memory or processing power, or if you want to speed up model inference without a significant loss in accuracy.
Not ideal if your primary concern is developing the initial model architecture or training it from scratch, as this tool focuses on post-training optimization.
Stars
12
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 11, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/approx-ml/approx"
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...