https://github.com/gsurma/deep_dream

DeepDream psychodelic image generator.
https://github.com/gsurma/deep_dream

artificial-intelligence cnn convolutional-neural-networks deep-dream deep-dreaming deep-learning deep-neural-networks inception machine-learning python python3 style-transfer tensorflow tensorflow-examples

Last synced: 3 months ago
JSON representation

DeepDream psychodelic image generator.

Host: GitHub
URL: https://github.com/gsurma/deep_dream
Owner: gsurma
License: mit
Created: 2019-10-19T15:29:31.000Z (over 5 years ago)
Default Branch: master
Last Pushed: 2021-07-09T08:50:26.000Z (almost 4 years ago)
Last Synced: 2025-01-31T03:12:26.021Z (3 months ago)
Topics: artificial-intelligence, cnn, convolutional-neural-networks, deep-dream, deep-dreaming, deep-learning, deep-neural-networks, inception, machine-learning, python, python3, style-transfer, tensorflow, tensorflow-examples
Language: Python
Homepage: https://gsurma.github.io
Size: 49.3 MB
Stars: 39
Watchers: 2
Forks: 15
Open Issues: 1
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE

Awesome Lists containing this project

README

# Deep Dream

Minimal Python/TensorFlow implementation of the DeepDream algorithm originally created by [Alexander Mordvintsev](https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html).

Daily dose of deep dreams on instagram.

## Usage

To use on the predefined .jpg image:

python3 deep_dream.py

python3 deep_dream.py

to perform on the random image.

## How does it work?

We are using **Inception5h** model which was designed to classify images.

During the classification process we are providing input images and using gradient descent to adapt weights to the images through filters.

**DeepDream** algorithm does the opposite. It adapts the input images to match the network weights with **gradient ascent** which results in visualizing network filters on the input images giving them psychodelic look.

## Results