Model Inspection and Visualization Tools

llmfit helps people choosing models for their own computers compare what will fit in memory and how fast it might run. It checks your hardware before recommending models, so you can assess candidates before downloading them.

TensorBoard helps ML developers and researchers inspect TensorFlow experiments through a browser. It shows how training progresses and lets you compare runs when evaluating changes to a model or its hyperparameters.

InterpretML is an open-source Python library for data scientists who need to explain machine learning predictions or build models whose decisions they can inspect directly. It runs locally on Windows, macOS and Linux under the MIT license. Its tools support model debugging and checks for potential bias, including work in healthcare and finance.

MediaPipe is a toolkit for developers adding on-device AI to applications. It provides pretrained models and task APIs for applications that need to process images, video, text or audio on the user's device.

Amphion is an audio generation toolkit for researchers and engineers developing speech and singing systems. It brings model implementations, dataset preparation and evaluation into one research codebase.

Captum is a Python library for examining what contributes to a PyTorch model's predictions, including input features, learned concepts and training examples. It's for model developers investigating unexpected results, application engineers explaining predictions, and researchers comparing interpretability methods. It works with most PyTorch model types with little modification to the model itself.

PyTorch Forecasting is a Python library for developers and researchers who want to predict time series with neural networks on their own hardware. It combines ready-made forecasting architectures with data preparation, training, and evaluation tools. It's open source under the MIT license.

DiCE is an open-source Python library that finds changes to an input that would make a machine learning model produce a different result. It's for model developers and researchers who need to explain individual predictions or examine a model's dependence on particular features. It generates several alternatives, so people can compare different routes to the desired prediction.

BERTopic is an open-source Python library for researchers and developers who need to find themes in document collections. It groups texts using transformer embeddings, then uses class-based TF-IDF to identify words that describe each group. Those keywords give you a way to inspect what a topic covers and which documents belong to it. The license is MIT.

gollama is a terminal app for people managing a local LLM collection in Ollama. Its keyboard-driven interface helps you compare downloaded models and clear out ones you don't need.

Fairlearn is an open-source Python toolkit for data scientists who need to examine how machine learning models affect different groups of people. It combines fairness assessment metrics with algorithms for reducing observed disparities, under the MIT license.

Netron visualizes neural network and machine learning models for developers and researchers who want to examine their structure.

StyleGAN3 is NVIDIA's local AI image generation and training software for researchers and developers. Its architecture addresses generated detail that stays fixed to pixel positions instead of following the depicted objects as they move.

SHAP is a Python library for data scientists and machine learning researchers who need to understand how input features contribute to a model's predictions. It uses Shapley values from game theory to assign contributions to individual features. The library is open source under the MIT license and runs in your own Python environment.

Embedding Atlas helps researchers and developers inspect embedding datasets and the records behind them. It makes clusters, outliers, and relationships visible alongside the data's metadata.

FiftyOne is a local tool for computer vision teams that need to inspect their training data and understand where their models fail. It runs on macOS, Windows and Linux, with Docker support, and is open source under Apache 2.0. Its Python tools and visual App connect dataset curation with model evaluation.