megvii-research/Sparsebit
A model compression and acceleration toolbox based on pytorch.
This toolkit helps machine learning researchers and engineers make their large neural network models smaller and faster. You provide an existing PyTorch model, and the toolkit applies compression techniques like pruning and quantization. The output is a more compact and efficient model that performs similarly but requires less computational power and memory, making it easier to deploy on resource-constrained hardware.
332 stars. No commits in the last 6 months.
Use this if you need to optimize large deep learning models for faster inference or deployment on devices with limited memory and processing power, without significantly sacrificing accuracy.
Not ideal if you are a data scientist or analyst looking for a no-code solution to optimize pre-trained models, as this tool requires familiarity with PyTorch and model development.
Stars
332
Forks
37
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/megvii-research/Sparsebit"
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...