Eclipsess/CHIP_NeurIPS2021
Code for CHIP: CHannel Independence-based Pruning for Compact Neural Networks (NeruIPS 2021).
This project helps machine learning engineers reduce the size and computational demands of neural networks for image classification tasks. By analyzing the independence of channels within a pre-trained model like ResNet or VGG, it identifies and removes redundant parts. You provide a pre-trained image classification model and dataset, and it outputs a more compact, pruned model that performs similarly but requires fewer resources.
No commits in the last 6 months.
Use this if you need to deploy large image classification models to environments with limited memory or processing power, such as mobile devices or embedded systems, without significantly sacrificing accuracy.
Not ideal if you are developing new deep learning architectures from scratch or if your primary goal is to improve model accuracy rather than efficiency.
Stars
39
Forks
6
Language
Python
License
—
Category
Last pushed
Sep 10, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Eclipsess/CHIP_NeurIPS2021"
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
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...