# fastai: A Layered API for Deep Learning

arXiv: https://arxiv.org/abs/2002.04688 · HTML: https://mlsanity.com/paper/2002.04688/

## Key facts

- Cited by 183 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 30 of 183)

- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [XTab: Cross-table Pretraining for Tabular Transformers](https://mlsanity.com/paper/2305.06090/) (2023)
- [R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.16341/) (2024)
- [Erasing Undesirable Influence in Diffusion Models](https://mlsanity.com/paper/2401.05779/) (2024)
- [ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning](https://mlsanity.com/paper/2405.19237/) (2024)
- [Learning to Estimate Shapley Values with Vision Transformers](https://mlsanity.com/paper/2206.05282/) (2022)
- [Dataset Distillation with Neural Characteristic Function: A Minmax Perspective](https://mlsanity.com/paper/2502.20653/) (2025)
- [Efficient and Effective Augmentation Strategy for Adversarial Training](https://mlsanity.com/paper/2210.15318/) (2022)
- [Generative Artificial Intelligence: A Systematic Review and Applications](https://mlsanity.com/paper/2405.11029/) (2024)
- [One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision](https://mlsanity.com/paper/2102.02320/) (2021)
- [Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning](https://mlsanity.com/paper/2405.07288/) (2024)
- [The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods](https://mlsanity.com/paper/2203.02486/) (2022)
- [PyThaiNLP: Thai Natural Language Processing in Python](https://mlsanity.com/paper/2312.04649/) (2023)
- [Separable Multi-Concept Erasure from Diffusion Models](https://mlsanity.com/paper/2402.05947/) (2024)
- [CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models](https://mlsanity.com/paper/2505.12677/) (2025)
- [On Efficient Training of Large-Scale Deep Learning Models: A Literature Review](https://mlsanity.com/paper/2304.03589/) (2023)
- [Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models](https://mlsanity.com/paper/2503.19783/) (2025)
- [Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers](https://mlsanity.com/paper/2103.14453/) (2021)
- [Augmenting medical image classifiers with synthetic data from latent diffusion models](https://mlsanity.com/paper/2308.12453/) (2023)
- [PyTorch Tabular: A Framework for Deep Learning with Tabular Data](https://mlsanity.com/paper/2104.13638/) (2021)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging](https://mlsanity.com/paper/2106.15944/) (2021)
- [Nonlinear Processing with Linear Optics](https://mlsanity.com/paper/2307.08533/) (2023)
- [Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization](https://mlsanity.com/paper/2504.09039/) (2025)

## Abstract (arXiv)

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library. fastai includes: a new type dispatch system for Python along with a semantic type hierarchy for tensors; a GPU-optimized computer vision library which can be extended in pure Python; an optimizer which refactors out the common functionality of modern optimizers into two basic pieces, allowing optimization algorithms to be implemented in 4-5 lines of code; a novel 2-way callback system that can access any part of the data, model, or optimizer and change it at any point during training; a new data block API; and much more. We have used this library to successfully create a complete deep learning course, which we were able to write more quickly than using previous approaches, and the code was more clear. The library is already in wide use in research, industry, and teaching. NB: This paper covers fastai v2, which is currently in pre-release at http://dev.fast.ai/