megvii-research/SSQL-ECCV2022
PyTorch implementation of SSQL (Accepted to ECCV2022 oral presentation)
This project helps machine learning engineers and researchers optimize deep learning models for deployment on resource-constrained devices. It takes an existing, unquantized self-supervised model and trains it to maintain high accuracy even when significantly compressed (quantized to lower bit-widths). The output is a single, compact model that performs well across various bit-width settings, making it versatile for different deployment scenarios.
No commits in the last 6 months.
Use this if you need to deploy high-accuracy computer vision models on hardware with limited memory or computational power, while retaining flexibility in model size.
Not ideal if your primary goal is general model pre-training without specific concerns about quantization or on-device deployment.
Stars
73
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/megvii-research/SSQL-ECCV2022"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)