Filter-Pruning-Geometric-Median

Visit Tool

filter-pruning-geometric-median is an Open Source Research & Education tool that accelerates deep convolutional neural networks through filter pruning. It implements the Geometric Median method for model compression, primarily using PyTorch.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is filter-pruning-geometric-median?

filter-pruning-geometric-median is an open-source implementation of the Filter Pruning via Geometric Median method for accelerating deep convolutional neural networks. Developed in PyTorch, this tool enables researchers and developers to reduce the computational cost and memory footprint of their models without significant loss in accuracy. It supports both network-level and layer-level sparsity configurations, offering flexibility in how pruning is applied. The repository provides detailed usage instructions for integration with PyTorch and NNI, along with scripts for reproducing results on datasets like ImageNet and CIFAR-10, making it a valuable resource for model compression research and application.

Best used for

Ideal for developers and data scientists who need to accelerate deep convolutional neural networks, compress model sizes for efficient deployment, and reproduce state-of-the-art research in model pruning. Especially valuable for those working with PyTorch and seeking to optimize model performance and resource usage.

Common actions

accelerate neural networks

prune deep learning models

compress convolutional networks

reproduce research results

collaborationopen-sourcelow-code/no-codedeepfakeautomated workflow"AI Agents"face swappingworkflowsgithub copilot

Capabilities

Key features

Filter pruning via geometric median
Deep convolutional neural network acceleration
PyTorch implementation
NNI integration
Network-level sparsity control
Layer-level sparsity control
Reproducible research scripts

Target Audience

developerdata scientist

Integrations

pytorchnni

Pricing & Plans

Open Source

Free

FAQs

What deep learning frameworks does filter-pruning-geometric-median support?

This tool primarily supports PyTorch for its implementation of filter pruning. Additionally, it provides integration with NNI (Neural Network Intelligence), a toolkit for automated machine learning, allowing for broader application within the PyTorch ecosystem.

Can I reproduce the research results from the CVPR 2019 paper using this repository?

Yes, the repository includes specific scripts designed to reproduce the results presented in the CVPR 2019 paper, "Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration." These scripts cover training and pruning for models like ResNet and VGGNet on datasets such as ImageNet and CIFAR-10.

What are the system requirements for running filter-pruning-geometric-median?

To run this implementation, you will need Python 3.6, PyTorch 0.3.1, and TorchVision 0.3.0. It's important to note the specific TorchVision version, as older versions might require adjustments to image transformation functions like `RandomResizedCrop`.

Trending

Subcategories trending in Research & Education

Academic Research Study Assistants Knowledge Management Course Creation Summarization Language Learning

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce