Utkarsh Singhal's starred repositories
the-art-of-debugging
The Art of Debugging
gligen-gui
An intuitive GUI for GLIGEN that uses ComfyUI in the backend
hlb-CIFAR10
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
awesome-experimental-standards-deep-learning
Repository collecting resources and best practices to improve experimental rigour in deep learning research.
ControlNet
Let us control diffusion models!
tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
gradient-descent-the-ultimate-optimizer
Code for our NeurIPS 2022 paper
latex-resources
Collection of LaTeX resources and examples.
pylustrator
Visualisations of data are at the core of every publication of scientific research results. They have to be as clear as possible to facilitate the communication of research. As data can have different formats and shapes, the visualisations often have to be adapted to reflect the data as well as possible. We developed Pylustrator, an interface to directly edit python generated matplotlib graphs to finalize them for publication. Therefore, subplots can be resized and dragged around by the mouse, text and annotations can be added. The changes can be saved to the initial plot file as python code.
pytorch-lightning
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
loss-landscapes
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch