https://github.com/AnjieCheng/MnasNet-PyTorch

A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
https://github.com/AnjieCheng/MnasNet-PyTorch

architecture-search mnasnet mobilenetv2 pytorch

Last synced: about 1 month ago
JSON representation

A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.

• Host: GitHub
• URL: https://github.com/AnjieCheng/MnasNet-PyTorch
• Owner: AnjieCheng
• Created: 2018-08-04T08:26:17.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-08-15T07:57:08.000Z (over 6 years ago)
• Last Synced: 2024-07-31T22:12:46.063Z (4 months ago)
• Topics: architecture-search, mnasnet, mobilenetv2, pytorch
• Language: Python
• Size: 6.84 KB
• Stars: 271
• Watchers: 12
• Forks: 51
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-image-classification - unofficial-pytorch : https://github.com/AnjieZheng/MnasNet-PyTorch
• awesome-image-classification - unofficial-pytorch : https://github.com/AnjieZheng/MnasNet-PyTorch
• awesome-AutoML-and-Lightweight-Models - AnjieZheng/MnasNet-PyTorch

README

        
# Overview

A PyTorch implementation of Mnasnet searched architecture: [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://arxiv.org/abs/1807.11626). On the ImageNet classification task, the model achieves 74.0% top-1 accuracy with 76ms latency on a Pixel phone, which is 1.5× faster than MobileNetV2

# MnasNet Architecture

![Alt text](https://i.imgur.com/ryyU8cP.png)

# Disclaimer

Codes modified from [mobilenet-v2](https://github.com/tonylins/pytorch-mobilenet-v2)