Katherine Crowson

CLOOB training (JAX) and inference (JAX and PyTorch)

crowsonkb

A CLIP conditioned Decision Transformer.

crowsonkb

A parallel implementation of the Deep Dream image processing algorithm which is able to process arbitrarily large images.

crowsonkb

ESGD-M is a stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch.

crowsonkb

Neural style transfer in PyTorch.

crowsonkb

Data-parallel image stylization using Caffe.

crowsonkb

Karras et al. (2022) diffusion models for PyTorch

crowsonkb

Image restoration with neural networks but without learning.

crowsonkb

GLIDE: a diffusion-based text-conditional image synthesis model

crowsonkb

crowsonkb