/Deep-learning-with-cats

Deep learning with cats (^._.^)

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

Deep-learning-with-cats

This repository is a "toy" project so I can gain experience building deep neural networks. My first goal is generating pictures of cats using Generative Adversarial Networks. My second goal is making art with cats by applying styles to pictures of cats using deep convolutional neural networks. (^._.^)

Updates

  • 17/07/2017 : Added CycleGAN for style transfer, so far doesn't work well with the CAT dataset and it's so slow (20-24h to fully train it). I'm leaving it here for those interested but I probably will try fast neural style instead.
  • 15/07/2017 : Many people were concerned about whether the generated images are really novel or rather just copies of the training dataset so I made a python function that output the 5 most similar training (real) images to the given generated (fake) images. See: https://github.com/AlexiaJM/Generative-model-most-similar-images.

Objectives (so far)

Needed

To run

$ # Download dataset and preprocess cat pictures 
$ # Create two folders, one for cats bigger than 64x64 and one for cats bigger than 128x128
$ sh setting_up_script.sh
$ # Move to your favorite place
$ mv cats_bigger_than_64x64 "your_input_folder_64x64"
$ mv cats_bigger_than_128x128 "your_input_folder_128x128"
$ # Generate 64x64 cats using DCGAN
$ python DCGAN.py --input_folder "your_input_folder_64x64" --output_folder "your_output_folder"
$ # Generate 128x128 cats using DCGAN
$ python DCGAN.py --input_folder="your_input_folder_128x128" --image_size 128 --G_h_size 64 --D_h_size 64 --SELU True
$ # Generate 64x64 cats using WGAN
$ python WGAN.py --input_folder "your_input_folder_64x64" --output_folder "your_output_folder"
$ # Generate 64x64 cats using WGAN-GP
$ python WGAN-GP.py --input_folder "your_input_folder_64x64" --output_folder "your_output_folder" --SELU True
$ # Generate 64x64 cats using LSGAN (Least Squares GAN)
$ python LSGAN.py --input_folder "your_input_folder_64x64" --output_folder "your_output_folder"

To see TensorBoard plots of the losses

$ tensorboard --logdir "your_input_folder"

Results

Discussion of the results at https://ajolicoeur.wordpress.com/cats.

DCGAN 64x64

DCGAN 128x128 with SELU

WGAN 64x64

WGAN-GP 64x64 with SELU