### Revisiting ResNets: Improved Training and Scaling Strategies

[LEARN MORE](/content/wandb_fc/pytorch-image-models/reports/Revisiting-ResNets-Improved-Training-and-Scaling-Strategies--Vmlldzo2NDE3NTM/index.html)

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

[LEARN MORE](/content/borisd13/demo_config/reports/Visualize-Track-and-Compare-fastai-Models-With-Weights-Biases--Vmlldzo4MzAyNA/index.html)

---

### 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](/content/capecape/miniai_ddpm/reports/Next-Frame-Prediction-Using-Diffusion-The-fastai-Approach--VmlldzozMzcyMTYy/index.html)  
**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](/content/fastai/fine_tune_timm/reports/Leveraging-Pre-Trained-Models-for-Image-Classification---VmlldzoxOTgyMTQ0/index.html)  
**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](/content/capecape/imagenette_timm/reports/Checking-Out-the-New-fastai-timm-Integration--VmlldzoxOTMzNzMw/index.html)  
**Transfer Learning: Serial versus One-time Training**  
Using Transfer Learning in Systematically Determining Adequacy of Dataset Size
[Read more](/content/maria_rodriguez/Transfer_learning_vf/reports/Transfer-Learning-Serial-versus-One-time-Training--VmlldzoxMjczNDMz/index.html)

### 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](/content/morgan/activations/reports/Visualize-Failure-Debugging-with-Model-Activations--Vmlldzo1MDA0NjY/index.html)  
**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](/content/fastai_community/reformer-fastai/reports/Reformer-The-Efficient-Transformer--Vmlldzo0MzQ1OTg/index.html)

### 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](/content/ai-fast-track/icevision-fridge/reports/IceVision-Meets-Weights-Biases-For-Object-Detection---VmlldzoyODQxNjg/index.html)  
**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](/content/jhartquist/fastaudio-esc-50/reports/Fine-Tuning-ResNet-18-for-Audio-Classification--VmlldzoyNjU3OTQ/index.html)  
**Visualize Fastai Faster**  
We're excited to announce a nice integration with fastai.
[Read more](/content/wandb_fc/articles/reports/Visualize-Fastai-Faster--Vmlldzo1NDY0Nzc3/index.html)  
**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](/content/stacey/deep-drive/reports/Semantic-Segmentation-The-View-from-the-Driver-s-Seat--Vmlldzo1MTg5NQ/index.html)  
**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](/content/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk/index.html)

---

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