Weights & Biases

Revisiting ResNets: Improved Training and Scaling Strategies

LEARN MORE

Visualize, Track, and Compare fastai Models With Weights & Biases

LEARN MORE

Computer Vision

Next Frame Prediction Using Diffusion: The fastai Approach
In this article, we look at how to use diffusion models to predict the next frame on a sequence of images, and we iterate fast over the MovingMNIST dataset. Read more
Leveraging Pre-Trained Models for Image Classification
In this article, we fine-tune a pre-trained model on a new classification dataset, to understand how well transfer learning helps the model train on new data. Read more
Checking Out the New fastai/timm Integration
In this article, we'll explore how ML practitioners can leverage the full timm backbone catalog in their deep learning pipelines with the new fastai integration. Read more
Transfer Learning: Serial versus One-time Training
Using Transfer Learning in Systematically Determining Adequacy of Dataset Size Read more

NLP

Visualize Failure - Debugging with Model Activations
Visualising your model's activations can help you spot if your model is training sub-optimally, even if the model appears to train "successfully". Read more
Reformer: The Efficient Transformer
Our fast.ai community submission to the Reproducibility challenge 2020: "Reformer: The Efficient Transformer" by Nikita Kitaev, Łukasz Kaiser and Anselm Levskaya, accepted to ICLR 2020. Read more

Computer Vision

IceVision Meets Weights & Biases For Object Detection
In this article, we look at how IceVision works with W&B to provide an agnostic object detection framework with outstanding experiment tracking. Read more
Fine-Tuning ResNet-18 for Audio Classification
This article presents reproducible experiments using fastai, fastaudio, and Weights & Biases Sweeps to explore hyperparameters for achieving high accuracy on the ESC-50 dataset. Read more
Visualize Fastai Faster
We're excited to announce a nice integration with fastai. Read more
Semantic Segmentation: The View from the Driver's Seat
This article explores semantic segmentation for scene parsing on Berkeley Deep Drive 100K (BDD100K) including how to distinguish people from vehicles. Read more
Visualize & Debug Machine Learning Models
This guide helps you get started with Weights & Biases in 5 minutes, giving the steps you need to take, the benefits, and some examples. Read more

Iterate on AI agents and models faster. Try Weights & Biases today.