Kalray/deeplabv3plus-mobilenetv2

Introduction

This repository stores the model for Deeplabv3plus-mobilenetv2, compatible with Kalray's neural network API.
Please see www.github.com/kalray/kann-models-zoo for details and proper usage.

Contents

• ONNX: deeplab-mb2_bilinear.onnx, deeplab-mb2_asym_floor.onnx (converted from tensorflow model)
• Tensorflow: deeplab_mobilenetv2_voc2012_513x513.pb

Reference links

• github: https://github.com/tensorflow/models/blob/archive/research/deeplab/g3doc/model_zoo.md
• weights: http://download.tensorflow.org/models/deeplabv3_mnv2_pascal_trainval_2018_01_29.tar.gz

Lecture reference

@inproceedings{deeplabv3plus2018,
  title={Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation},
  author={Liang-Chieh Chen and Yukun Zhu and George Papandreou and Florian Schroff and Hartwig Adam},
  booktitle={ECCV},
  year={2018}
}

@inproceedings{mobilenetv22018,
  title={MobileNetV2: Inverted Residuals and Linear Bottlenecks},
  author={Mark Sandler and Andrew Howard and Menglong Zhu and Andrey Zhmoginov and Liang-Chieh Chen},
  booktitle={CVPR},
  year={2018}
}

Author: qmuller@kalrayinc.com