K0EKJE/CNN_compression_with_Tensor_Decomposition
Research in compressing convolutional layers of CNN using low-rank Tucker tensor decomposition
This project helps machine learning engineers and researchers reduce the memory footprint and speed up the inference time of deep convolutional neural networks (CNNs), especially for image classification tasks. It takes an existing trained CNN model and outputs a smaller, faster model with minimal loss in prediction accuracy. This is ideal for deploying powerful AI models on devices with limited computational resources.
No commits in the last 6 months.
Use this if you need to deploy a large deep learning model on resource-constrained devices like mobile phones or embedded systems and want to reduce its size and improve its speed.
Not ideal if your primary goal is to improve model accuracy or if you are not working with convolutional neural networks.
Stars
11
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/K0EKJE/CNN_compression_with_Tensor_Decomposition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained...
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)