Skip to content

hjptriplebee/deep_dream_tensorflow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

deep_dream_tensorflow

An implement of google deep dream with tensorflow. Detailed description can be found here

Demo:

Requirement

  • Python3
  • OpenCV
  • tensorflow 1.0

Usage

-python3 main.py --input {input path} --output {output path}

If you don't input any image, it will generate a dream image with noise.

Tips

Gradient ascent region has uncertainty, even same image with same parameters can generate different pictures.

Larger "iter_num" means a more surprising and more different image.

larger receptive field means more semantic information.

To different image, best parameters are different.

About

An implement of google deep dream with tensorflow

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages