Katharina Prasse's starred repositories
hungarian-algorithm
Python 3 implementation of the Hungarian Algorithm
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
imagenette
A smaller subset of 10 easily classified classes from Imagenet, and a little more French
bottom-up-attention.pytorch
A PyTorch reimplementation of bottom-up-attention models
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
webdataset
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
CLIP_benchmark
CLIP-like model evaluation
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
WaffleCLIP
Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts"
natural-adv-examples
A Harder ImageNet Test Set (CVPR 2021)
ConvNeXt-V2
Code release for ConvNeXt V2 model
imagenet-r
ImageNet-R(endition) and DeepAugment (ICCV 2021)
big_vision
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
vision-language-models-are-bows
Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023
grid-feats-vqa
Grid features pre-training code for visual question answering