Popular GitHub Repositories for Weights And Biases

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

A clean and structured implementation of Transformer with wandb and pytorch-lightning

:dart: Deep Learning Framework for Image Classification & Regression in Pytorch for Fast Experiments

This repository focuses on training semantic segmentation models to predict the presence of floodwater for disaster prevention. Models were trained using SageMaker and Colab.

PyTorch Lightning Implementation of Diffusion, GAN, VAE, Flow models

Example codes in the medium post titled "Optuna meets Weights and Biases."

Tiny ResNet inspired FPN network (<2M params) for Rotated Object Detection using 5-parameter Modulated Rotation Loss

Order execution in the financial markets using Deep Reinforcement Learning.

:detective::robot: Monitoring a PyTorch Lightning CNN with Weights & Biases

Deep learning based color transfer between images.

A template repository to quickly get started on a new Machine Learning project.

Using GPT-3 to help me get more ? on medium.com

Machine learning and AI projects require managing diverse data sources, vast data volumes, model and parameter development, and conducting numerous test and evaluation experiments. Overseeing and tracking these aspects of a program can quickly become an overwhelming task.

Predicting Turbine Energy Yield (TEY) using ambient variables as features.

Official Course Webpage for CS175: Projects in AI

Training Fashion product classification and visual similarity detection model using Pytorch Lightning

Templates for AI projects.

A Low-Rank Adaptation of a pretrained Stable Diffusion model that generates background scenery. Trained with PyTorch, and deployed with AWS EC2 and Ngrok.

Llama3 Trainer aims to provide a CLI interface to orchestrate the fine-tuning of open source AI models, such as Llama3, using 3rd party services, such as [Lambda Cloud](https://lambdalabs.com/), [Hugging Face](https://huggingface.co/) and [Weights & Biases](https://wandb.ai).

Machine Learning pipeline training Convolutional Neural Networks to identify sports vs advertisement images