Tencent/PocketFlow
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
This framework helps machine learning engineers and AI application developers shrink large deep learning models for faster performance on devices with limited computing power, like mobile phones. You provide your existing deep learning model and specify desired compression or speed-up ratios. The framework then automatically outputs a smaller, faster model ready for deployment, maintaining accuracy as much as possible.
2,914 stars. No commits in the last 6 months.
Use this if you need to deploy your deep learning models for tasks like computer vision or speech recognition on mobile devices or other resource-constrained environments.
Not ideal if you are working with traditional machine learning models or if computational efficiency is not a primary concern for your deployment target.
Stars
2,914
Forks
492
Language
Python
License
—
Category
Last pushed
Mar 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tencent/PocketFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit...
mlcommons/inference
Reference implementations of MLPerf® inference benchmarks
mlcommons/training
Reference implementations of MLPerf® training benchmarks
datamade/usaddress
:us: a python library for parsing unstructured United States address strings into address components
GRAAL-Research/deepparse
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning