metadata

license: mit
datasets:
  - ILSVRC/imagenet-1k
pipeline_tag: image-classification

Introduction

This repository stores the model for Regnet-x-8.0g, compatible with Kalray's neural network API.
Please see www.github.com/kalray/kann-models-zoo for details and proper usage.
Please see https://huggingface.co/docs/transformers/main/en/model_doc/regnet for Regnet model description.

ONNX: regnet-x-8g.onnx
Quantized ONNX (INT8): regnet-x-8g-q.onnx

Lecture note reference

Designing Network Design Spaces, https://arxiv.org/pdf/2003.13678.pdf

Repository or links references

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2003-13678,
  author       = {Ilija Radosavovic and
                  Raj Prateek Kosaraju and
                  Ross B. Girshick and
                  Kaiming He and
                  Piotr Doll{\'{a}}r},
  title        = {Designing Network Design Spaces},
  journal      = {CoRR},
  volume       = {abs/2003.13678},
  year         = {2020},
  url          = {https://arxiv.org/abs/2003.13678},
  eprinttype   = {arXiv},
  eprint       = {2003.13678},
  timestamp    = {Thu, 02 Apr 2020 15:34:08 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2003-13678.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@InProceedings{Radosavovic2019,
  title = {On Network Design Spaces for Visual Recognition},
  author = {Ilija Radosavovic and Justin Johnson and Saining Xie Wan-Yen Lo and Piotr Doll{\'a}r},
  booktitle = {ICCV},
  year = {2019}
}

@InProceedings{Radosavovic2020,
  title = {Designing Network Design Spaces},
  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{\'a}r},
  booktitle = {CVPR},
  year = {2020}
}

@InProceedings{Dollar2021,
  title = {Fast and Accurate Model Scaling},
  author = {Piotr Doll{\'a}r and Mannat Singh and Ross Girshick},
  booktitle = {CVPR},
  year = {2021}
}

Authors:

Kalray
/

regnet-x-8.0g

Introduction

Contents

Lecture note reference

Repository or links references