This pull request includes a Dockerfile that packages FastGAN in a reproducible Docker image. I've pushed the image to the Replicate Docker registry and included a link in the README: https://beta.replicate.ai/odegeasslbc/FastGAN
For the Docker image I wrote a small infer.sh script that switches between model types (art, face, dog, etc.). There's a little hack in Dockerfile.cpu that makes the pre-trained models work on CPU as well.
We are working to make Replicate a registry of machine learning models that can be easily reproduced. With Docker the models can be run "forever", without having to worry about missing dependencies. The website design is still a work in progress, so it might look a little rough around the edges.
This pull request includes a Dockerfile that packages FastGAN in a reproducible Docker image. I've pushed the image to the Replicate Docker registry and included a link in the README: https://beta.replicate.ai/odegeasslbc/FastGAN
For the Docker image I wrote a small
infer.shscript that switches between model types (art,face,dog, etc.). There's a little hack inDockerfile.cputhat makes the pre-trained models work on CPU as well.We are working to make Replicate a registry of machine learning models that can be easily reproduced. With Docker the models can be run "forever", without having to worry about missing dependencies. The website design is still a work in progress, so it might look a little rough around the edges.