All Posts

Jun 14, 2022

Discovering and Debugging a PyTorch Performance Decrease
Subclassed Tensors Reduce GPU Throughput up to Forty Percent

Over the past week, Thomas Capelle and I discovered, debugged, and created a workaround for a performance bug in PyTorch which reduced image training GPU throughput up to forty percent when using fastai. The culprit? Subclassed tensors.

Jun 6, 2022

Introducing fastxtend
A Collection of Tools, Extensions, & Addons for fastai

Fastxtend is a collection of tools, extensions, and addons for fastai. In this post, I highlight some of fastxtend’s current best features.

Mar 11, 2022

Detecting Cloud Cover Via Sentinel-2 Satellite Data
My Top-10 Percent Solution to DrivenData’s On CloudN Competition

In this post I will give an overview of my solution, explore some of my alternate solutions which didn’t perform as well, and give a quick overview on how to customize fastai to work on a new dataset.

Dec 8, 2021

Testing Amazon SageMaker Studio Lab
Comparing SageMaker to Google Colab and Kaggle

SageMaker is a strong contender for those starting out in deep learning and almost a straight upgrade from the free version of Colab. Compared to Kaggle and Colab Pro's P100, SageMaker's T4 can be faster in Mixed Precision training, while significantly slower in single precision training.

Oct 1, 2021

Inference With fast.ai
Model Saving, Loading, and Prediction

In this tutorial I cover how to use fast.ai for inference, how to save and load fast.ai models, and how to avoid the few pitfalls along the way.

Jul 19, 2021

Benchmarking PyTorch’s Native Mish

PyTorch 1.9 added a native implementation of Mish, my go to activation function for computer vision tasks. In this post I benchmark the computational performance of native Mish on a Tesla V100, Tesla P100, and CPU and compare its speed to other Mish implementations and activation functions.