资源分类
》 资源 》算法》SqueezeNet-tf

SqueezeNet-tf

2020-01-09 | |  37 |   0 |   0

SqueezeNet-tf

A Tensorflow SqueezeNet implementation of the research https://arxiv.org/abs/1602.07360

What is SqueezeNet?

SqueezeNet is a convolutional neural network with 80.3% top-5 accuracy on the ImageNet dataset. This architecture aims to signifanctly reduce the size of the model.

Goals

  • Building the network

  • Training the network on imagenet

    • Currently published pre-trained weights cannot be used in TensorFlow, the goal of this project is to produce easy-to-use save files.

  • Neural Style Transfer (http://arxiv.org/abs/1508.06576) on mobile devices

    • Running on mobile devices in reasonable time without sacraficing quality too much like other feed-forward approaches.

图片.png

上一篇：SqueezeNet-Neural-Style-Pytorch

下一篇：Simplified_SqueezeNet

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...