Skip to content

Latest commit

 

History

History
14 lines (10 loc) · 1.38 KB

README.md

File metadata and controls

14 lines (10 loc) · 1.38 KB
Raw

Autoencoders-using-Pytorch

In this project, nuances of the autoencoder training were looked over.

  1. Autoencoder end-to-end training for classifying MNIST dataset. [Notebook01]
  2. Autoencoder Layer Wise Pre-training (Stacking) for Fashion-MNIST. [Notebook02]
  3. DRIVE (Digital Retinal Images for Vessel Extractions) dataset patchwise segmentation using Autoencoder. [Notebook03]
  4. Sparse Denoising Autoencoder (SDAE) for classification of MNIST dataset. [Notebook04, Notebook05]

Built With

License

This project is licensed under the MIT License - see the LICENSE.md file for details