Skip to content

flateon/Deep-Learning-Remote-Sensing-Image-Classification-Using-Pretrained-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Learning Remote Sensing Image Classification Using Pretrained Networks

Unofficial PyTorch implementation of paper Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks

Difference

Due to the lack of Overfeat's PyTorch Pre-trained model, we replace Overfeat with AlexNet which has a very similar structure

Requirements

To install requirements
conda env create -f environment.yml

Usage

  1. Clone this Repository
  2. Download and Unzip the UCMerced_LandUse dataset
  3. python train.py

Result

Metric Reported Our Implementation
Test-set accuracy 92.4% 93.57%

About

A PyTorch implementation of paper: Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks (https://ieeexplore.ieee.org/document/7342907)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages