There’s a common warning in pandas about a SettingWithCopyWarning. While the error message covers some of the possible reasons for the error, it doesn’t cover them all. In this post, I’ll show another source of the error and how to fix it.

This blog posts shows some ways to get generally good performance on tabular data. Most of the work in getting high performance models from tabular data comes from cleaning the dataset, clever feature engineering, and other tasks specific to the data set. We won’t be doing that here. However, there’s still a need for some good baseline parameters to know you’re getting the best out of your model. This post provides a way to use Bayesian optimization to find good hyperparameters and get good performance.

This post is a tutorial on working with tabular data using FastAI. One of FastAI’s biggest contributions in working with tabular data is the ease with which embeddings can be used for categorical variables. I have found that using embeddings for categorical variables results in significantly better models than the alternatives (e.g. one-hot encoding). I have found that the combination of embeddings and neural networks reach very high performance with tabular data.

In this tutorial, I will be looking at how to prepare a semantic segmentation dataset for use with FastAI. I will be using the Chest X-Ray Images (Pneumonia) dataset from Kaggle as an example. This post focuses on the components that are specific to semantic segmentation. To see tricks and tips for using FastAI with data in general, see my FastAI Data Tutorial - Image Classification.

In this tutorial, I will be looking at how to prepare an object detection dataset for use with PyTorch and FastAI. I will be using the DOTA dataset as an example. I will prepare the same data for both PyTorch and FastAI to illustrate the differences. This post focuses on the components that are specific to object detection. To see tricks and tips for using FastAI with data in general, see my FastAI Data Tutorial - Image Classification.

This post is a tutorial for loading data with FastAI. The interface has changed a lot since I originally wrote a FastAI data tutorial, so I deleted that one and I’m starting from scratch and making a brand new one. I’ll try to keep this up-to-date with the latest version. FastAI seems to be quite stable at the moment, so hopefully this will continue to work with the latest version.

Is it barbaric to write poetry after Auschwitz?