In this article, we examine the game theory based approach to explaining outputs of machine learning models: Shapely Additive exPlanations or SHAP. We then demo the technology using sample images in a Gradient Notebook.
In this article, we talk about what Dense Passage Retrieval is, how it works, and its uses. We also show how to implement it using the Simple Transformers python library in a Gradient Notebook.
In this tutorial, we show how to apply model interpretability algorithms from Captum on simple models. We demo building a basic model and use attribution algorithms such as Integrated Gradients, Saliency, DeepLift, and NoiseTunnel to attribute the image's label to the input pixels and visualize it.
In this article, we examine the processes of implementing training, undergoing validation, and obtaining accuracy metrics - theoretically explained at a high level. We then demonstrate them by combining all three processes in a class, and using them to train a convolutional neural network.
In this article, we explore what dimensions imply in a convolutional neural network context. We show how to create a custom convnet as a baseline model, and then proceed to create new versions of it, with increased width, increased depth and the last one with both increased depth and width.
This tutorial provides step-by-step instructions on how to handle class imbalances in image datasets for training computer vision models.
In this article, we took a look at data augmentation as an upsampling technique for handing class imbalance by looking at 5 sample methods. Thereafter, we augment a dataset and train it on a convnet using said dataset show how it improved accuracy and recall scores.
In this overview of Automatic Mixed Precision (AMP) training with PyTorch, we demonstrate how the technique works, walking step-by-step through the process of integrating AMP in code, and discuss more advanced applications of AMP techniques with code scaffolds to integrate your own code.
In this blogpost, we discuss the benefits and utilities of using PyTorch Lightning with Gradient Notebooks to optimize and simplify deep learning code, as well as extend the capabilities of Torch beyond the scope of the original package.
