Bigframes Alternatives

A simplified framework and utilities for PyTorch

Poutyne is an open source Python framework that removes much of the boilerplate involved in training neural networks with PyTorch. A developer writes a PyTorch module as usual and passes it to the Poutyne Model, which then runs the training loop, tracks statistics and applies callbacks. The design is openly inspired by...

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Deepparse is an open source Python library for parsing multinational street addresses with deep learning. Given a raw address string, it splits the text into labelled components such as street number, street name, municipality, province and postal code, using pretrained sequence to sequence models with or without an at...

Data Versioning and ML Experiments

DVC, short for Data Version Control, is an open source tool that brings Git style version control to data, models and machine learning experiments. It works as an extension of Git: large datasets and model files are tracked with small metadata files committed alongside the code, while the actual content lives in remote...

A lightweight AutoML library.

Falcon is a lightweight AutoML library for Python that trains a complete machine learning pipeline from a single call. Point it at a CSV file or a pandas data frame, name the task, and it handles preprocessing, candidate model selection and evaluation, returning a trained pipeline without the usual assembly work. It is...

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Foolbox is a Python library for running adversarial attacks against machine learning models. It takes a trained model, wraps it in a framework specific adapter, and applies an attack to a batch of inputs across a range of perturbation budgets, returning the adversarial examples and a success flag for each one. The purp...

The nnsight package enables interpreting and manipulating the internals of deep learned models.

NNsight is a Python library for interpreting and manipulating the internals of deep learning models. It gives researchers a Pythonic interface to read activations at any layer during a forward pass, modify those activations to study causal effects, and compute gradients with respect to intermediate values. It was devel...