Skip to content

haoyujack/pytorch-image-classification

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

PyTorch Image Classification

Classifies an image as containing either a dog or a cat (using Kaggle's public dataset), but could easily be extended to other image classification problems.

Dependencies:

  • PyTorch / Torchvision
  • Numpy
  • PIL
  • CUDA

Data

The data directory structure I used was:

  • project
    • data
      • train
        • dogs
        • cats
      • validation
        • dogs
        • cats
      • test
        • test

Performance

The result of the notebook in this repo produced a log loss score on Kaggle's hidden dataset of 0.04988 -- further gains can probably be achieved by creating an ensemble of classifiers using this approach.

About

Classifying cat and dog images using Kaggle dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%