Stars
Python bindings and improvements for a hough line based lens distortion corection algorithm
Hybrid ML + physics model of the Earth's atmosphere
Compressing weather and climate data into neural networks
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
WRF-SFIRE data acquisitiion, forecasting, data assimilation, and visualization in Python.
Flash Attention in ~100 lines of CUDA (forward pass only)
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework
Implement the nerf tutorial with keras and jax
Code for training non-parametric copula networks
An extremely fast Python package and project manager, written in Rust.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Fast, accurate watershed delineation using hybrid vector- and raster-based methods and data from MERIT-Hydro
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
SNAP: Self-supervised Neural Maps for Visual Positioning and Semantic Understanding (NeurIPS 2023)