-
Weights & Biases
- San Francisco, CA
- careyphelps.com
- @carey_phelps
Stars
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Porting the AnimeGan2 Model to Android
Top-level directory for documentation and general content
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Sparsity-aware deep learning inference runtime for CPUs
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Example deep learning projects that use wandb's features.
PyTorch Implementation for Deep Metric Learning Pipelines
(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…
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Experimental wandb CLI and Python API - See Experimental section below.
This is a collection of the code that accompanies the reports in The Gallery by Weights & Biases.
Tweet Generation with Huggingface
Work related to time series prediction and forecasting of Coronavirus
Implementation for the paper "Adversarial Continual Learning" in PyTorch.
This example shows how to run models and log the results to Weights and Biases while allowing your models to timeout after a certain amount of time.
Code for "Unsupervised State Representation Learning in Atari"
GitHub Action That Retrieves Model Runs From Weights & Biases
Classification of Simpsons characters using fast.ai
A curated list of articles that cover the software engineering best practices for building machine learning applications.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Always know what to expect from your data.
Learn how to design, develop, deploy and iterate on production-grade ML applications.
Conditional Transformer Language Model for Controllable Generation
Datasets, tools, and benchmarks for representation learning of code.
Humble microlibrary / command line tool for summarizing data within Weights and Biases across runs.
Keras implementation of RetinaNet object detection.