krasserm

krasserm's Stars

• cstub/python-project-template

  Python ML Project Template

  Language:Python31

• GEM-benchmark/NL-Augmenter

  NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

  Language:Python782195

• facebookresearch/AugLy

  A data augmentations library for audio, image, text, and video.

  Language:Python5k304

• microsoft/GLIP

  Grounded Language-Image Pre-training

  Language:Python2.4k204

• microsoft/SPTAG

  A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

  Language:C++4.9k585

• MaartenGr/BERTopic

  Leveraging BERT and c-TF-IDF to create easily interpretable topics.

  Language:Python6.6k803

• pytorch/data

  A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

  Language:Python1.2k161

• huggingface/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

  Language:Python33.7k4.9k

• criteo/autofaiss

  Automatically create Faiss knn indices with the most optimal similarity search parameters.

  Language:Python84575

• rom1504/clip-retrieval

  Easily compute clip embeddings and build a clip retrieval system with them

  Language:Jupyter Notebook2.5k222

• google-research-datasets/wit

  WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

  1k42

• johanmodin/clifs

  Contrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP

  Language:JavaScript46850

• salesforce/Merlion

  Merlion: A Machine Learning Framework for Time Series Intelligence

  Language:Python4.2k333

• piskvorky/gensim

  Topic Modelling for Humans

  Language:Python15.9k4.4k

• rom1504/img2dataset

  Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

  Language:Python4k350

• akandykeller/TopographicVAE

  Official implementation of the paper "Topographic VAEs learn Equivariant Capsules"

  Language:Python7915

• pallets/click

  Python composable command line interface toolkit

  Language:Python16.2k1.4k

• facebookresearch/fairscale

  PyTorch extensions for high performance and large scale training.

  Language:Python3.3k287

• yunjey/pytorch-tutorial

  PyTorch Tutorial for Deep Learning Researchers

  Language:Python31.1k8.2k

• google-deepmind/deepmind-research

  This repository contains implementations and illustrative code to accompany DeepMind publications

  Language:Jupyter Notebook13.7k2.7k

• mlfoundations/open_clip

  An open source implementation of CLIP.

  Language:Python11.4k1.1k

• hojonathanho/diffusion

  Denoising Diffusion Probabilistic Models

  Language:Python4.3k407

• lucidrains/denoising-diffusion-pytorch

  Implementation of Denoising Diffusion Probabilistic Model in Pytorch

  Language:Python9.1k1.1k

• google-deepmind/alphafold

  Open source code for AlphaFold 2.

  Language:Python13.4k2.4k

• ddangelov/Top2Vec

  Top2Vec learns jointly embedded topic, document and word vectors.

  Language:Python3k375

• Zasder3/train-CLIP

  A PyTorch Lightning solution to training OpenAI's CLIP from scratch.

  Language:Python68682

• sktime/sktime

  A unified framework for machine learning with time series

  Language:Python8.3k1.5k

• huggingface/accelerate

  🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

  Language:Python8.6k1.1k

• facebookresearch/vissl

  VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

  Language:Jupyter Notebook3.3k335

• openai/CLIP

  CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

  Language:Jupyter Notebook28.3k3.5k