Skip to content

Google's Inceptionism algorithm implementation in Pytorch with ResNet-x, VGG-x using MIT Indoor Scene dataset

License

Notifications You must be signed in to change notification settings

mnguyen0226/deepdream_college

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeepDream: What I Dreamt While At College

I experienced various vivid dream during college. Inceptionism Algorithm allows me to share my dream with you visually. Let's take a look!

alt-text

1. Gallery

alt-text

alt-text

Other Images

Architecture-specific Images

2. Explanation

VGG11, VGG16, VGG19, ResNet50, ResNet101, ResNet152 trained from scratch on MIT Indoor Scene dataset.

alt-text

3. Reproduction

python==3.8.5x
matplotlib
pytorch==1.8.1+cu111
opencv-contrib-python
opencv-python

Training script: src/notebooks/training

DeepDream script: src/notebooks/deepdream

Note: Due to the size of the trained model, I will attach the trained model in here.

4. Inspiration

Google AI Blog - "Inceptionism: Going Deeper into Neural Networks"

5. Report

Proposal

Final Report

About

Google's Inceptionism algorithm implementation in Pytorch with ResNet-x, VGG-x using MIT Indoor Scene dataset

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published