Skip to content

Conversation

tornupnegatives
Copy link

I'm very happy to have come across this project. I wanted to use deep dream to add some flair to a video project I'm working on, and I prefer PyTorch over TensorFlow... This PR introduces a few small changes to bring the repo "up-to-date":

  1. Adds a requirements.txt to make it easy to get started
  2. Inserts a few lines to automatically configure either a CUDA or Metal GPU
  3. Silences a warning about deprecated arguments to the vgg19 initializer
  4. Fixes an error with matplotlib wanting the output image data to be normalized

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant