There are 3 repositories under wandb topic.
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
PyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC)
Github repo with tutorials to fine tune transformers for diff NLP tasks
Train a state-of-the-art yolov3 object detector from scratch!
Generic template to bootstrap your PyTorch project.
(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.
PyTorch Implementations For A Series Of Deep Learning-Based Recommendation Models (IN PROGRESS)
Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)
Deep Learning project template for PyTorch (Distributed Learning is supported)
Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.
Tensorflow 2.3.0 implementation of DeepLabV3-Plus
A clean and structured implementation of Transformer with wandb and pytorch-lightning
KUIELAB-MDX-Net got the 2nd place on the Leaderboard A and the 3rd place on the Leaderboard B in the MDX-Challenge ISMIR 2021
A multibranch neural net architecture. (PyTorch)
Packaged deep reinforcement learning algorithms in tensorflow 2.x
A clean and structured implementation of the RNN family with wandb and pytorch-lightning
Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers
🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇
(ECCV 2020) This repo contains code for "DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning" (https://arxiv.org/abs/2004.13458), which extends vanilla DML with auxiliary and self-supervised features.
Unofficial Implementation of ECANets (CVPR 2020) for the Reproducibility Challenge 2020.
Automatically upload the model saved as W&B Artifact to Kaggle Dataset.
🥇KNOW기반 직업 추천 알고리즘 경진대회 1등 솔루션입니다🥇
Automated question generation and question answering from Turkish texts using text-to-text transformers
Utilities and boilerplate code to use wandb with allennlp
Utils and modules for Speech Language and Multimodal processing using pytorch and pytorch lightning
Helpful data preprocessing, training, and visualisation code and scripts for a range of Kaggle competitions, supported by Weights & Biases.
Exploring NLP weak supervision approaches to train text classification models. The project is also a prototype for a semi-automated text data labelling platform. Approaches: Snorkel and Zero-Shot Learning.
🤖 Project template for your next awesome AI project. 🦾
Tiny ResNet inspired FPN network (<2M params) for Rotated Object Detection using 5-parameter Modulated Rotation Loss
This project takes the arXiv dataset and builds an automatic tag classifier from the arXiv article/paper titles
We use phonetics as a feature to create a joint semantic-phonetic embedding and improve the neural machine translation between Chinese and Japanese. 🥳
🥈50th place in Bristol-Myers Squibb – Molecular Translation competition🥈
:detective::robot: Monitoring a PyTorch Lightning CNN with Weights & Biases
🥈42nd place in CommonLit Readability Prize competition🥈