DLNotebooks

Collection of Jupyter Notebook implementations from Deep Learning Papers I find interesting

To run locally:

 pip3 install -r requirements.txt
 jupyter notebook

Create a folder within the directory named datasets and add relevant datasets.
Please note that you're using Python3.7 or above

FSRCNN - Fast Super-Resolution Convolutional Neural Networks

FSRCNN trained on DIV2K dataset and a scaling factor of 4
paper : Accelerating the Super-Resolution Convolutional Neural Network,Chao Dong,et al.
dataset : DIV2K dataset
notebook : link
model : link

DCGAN - Deep Convolutional Generative Adversarial Networks

DCGAN trained on images of abstract art
paper : Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,Alec Radford, Luke Metz, Soumith Chintala
dataset : Abstract art datset
notebook : link
model : link
code used for overriding train step from here
model checkpoints are not included in the repo for this implementation