Skip to content

MobileNetV1 implemenation via Pytorch. Training with ImageNet1K dataset. Evaluate inference result. Measure inference speed and compare to other models (VGG16, GoogleNet)

scyonggg/Embedded_CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Embedded_CNN

This repository contains:

  • MobileNetV1 implemenation via Pytorch.
  • Training with ImageNet1K dataset from scratch.
  • Evaluate inference result.
    • Measure inference speed and compare to other models (VGG16, GoogleNet)

Model architecture

Train from scratch

MobileNet simple implementation in PyTorch

image

Evaluate inference speed

  • Measure inference time and compare to other models
    • MobileNet is faster for 2x times than GoogleNet and 6x times than VGG16
  • Refer to infer_speed.py for measurement code

About

MobileNetV1 implemenation via Pytorch. Training with ImageNet1K dataset. Evaluate inference result. Measure inference speed and compare to other models (VGG16, GoogleNet)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published