fastai

What fastai is

fastai is a free Python library designed to simplify training fast and accurate neural networks using modern practices. It offers high-level components for practitioners and lower-level components that researchers can combine into new approaches. Its quick start demonstrates image classification and segmentation, text sentiment, recommendation, and tabular models. The library includes a Python type dispatch system, GPU-optimized computer vision tools, an optimizer, callbacks, and a data block API. Installation is done with `pip install fastai`, with PyTorch recommended first; users can also work in Google Colab without installing it locally. Documentation pages are available as interactive notebooks. fastai can be used with other PyTorch-based libraries, and migration guides cover plain PyTorch, Ignite, Lightning, and Catalyst. The library supports local training, GPU acceleration, and distributed training. In Jupyter on Windows, fastai sets DataLoader `num_workers` to 0 to avoid hanging, which can make computer vision tasks many times slower than on Linux. The documentation recommends Windows Subsystem for Linux; this limitation does not apply when running fastai from a script.