Skip to content
/ Dynamic-Unet Public template

This project is the implementation of Dynamic U-Net architecture on Caravan Mask Challenge Dataset. A state of the art technique that has won many Kaggle competitions and is widely used in industry. Image segmentation models allow us to precisely classify every part of an image, right down to pixel level.

License

Notifications You must be signed in to change notification settings

ashutoshraj/Dynamic-Unet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

DynamicUnet

This project is the "error-free" implementation of Dynamic U-Net architecture on Caravan Mask Challenge Dataset. A state of the art technique that has won many Kaggle competitions and is widely used in industry. Image segmentation models allow us to precisely classify every part of an image, right down to pixel level. This code will be useful for anykind of binary instance classification.

Getting Started

For quick experiments, you can use Google Colab using caravan-work.ipynb You can also run the experiments locally.

Requirements

For running locally

  • Install PyTorch (pytorch.org)
  • Install Fastai
  • Download the data from here

For running in Colab

  • Everything is already installed
  • To download the data from here to your Colab VM, you can use CurlWget Chrome Extension
    • Note: You should keep a copy of the data in your Google Drive for later use.

Acknowledgments

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

License

MIT

About

This project is the implementation of Dynamic U-Net architecture on Caravan Mask Challenge Dataset. A state of the art technique that has won many Kaggle competitions and is widely used in industry. Image segmentation models allow us to precisely classify every part of an image, right down to pixel level.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published