fastai: A Layered API for Deep Learning

@article{Howard2020fastaiAL,
  title={fastai: A Layered API for Deep Learning},
  author={Jeremy Howard and Sylvain Gugger},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04688}
}
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… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 58 REFERENCES

Python: A dynamic, open source programming language

  • Python Core Team
  • Python Software Foundation,
  • 2019
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Automatic differentiation in PyTorch

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

TensorFlow: Large-Scale Machine

  • M. Abadi, A. Agarwal, +37 authors X. Zheng
  • Learning on Heterogeneous Systems,
  • 2015
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD

  • J. Howard, S. Gugger
  • 2020
VIEW 2 EXCERPTS