Stars
DeepFix an agent that automatically diagnoses common bugs in machine learning models and provides a prioritized list of research-backed solutions.
Digitizing Paper ECGs at Scale: An Open-Source Algorithm for Clinical Research
A python package for end-to-end geospatial machine learning using multispectral earth observation data such as NASA HLS and ESA Sentinel-2.
Agentic AI system to solve Kaggle Competitions
Official Pytorch implementation of EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens [ICML2024].
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
[CVPR 2024] Dual Prototype Attention for Unsupervised Video Object Segmentation
Implementation of MagViT2 Tokenizer in Pytorch
AI-powered application that allows you to chat with your documents. Upload PDFs, text files, or paste raw text, and get intelligent, context-aware answers from a powerful language model.
PyTorch implementation of the CortexNet predictive model
Implementation of Conv4d for PyTorch
Independent implementation of Supervised Contrastive Loss. Straight to the point and beyond
Solution for the RSNA STR Pulmonary Embolism Detection Kaggle challenge
PyTorch project template for distributed training and logging to local MLflow instance.
A Visual Question Answering (VQA) system that combines ResNet50 for image feature extraction and BERT for question understanding to accurately answer natural language questions about images using t…
An implementation of a mutli-head attention encoder that encorporates rotary positional encodings (RoPE) as described in Su et al. (2021, https://arxiv.org/abs/2104.09864).
A simple package for ultrasound ML data preprocessing
[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation
Can you identify where and when an urban flash flood happened in South Africa?