资源分类
》 资源 》算法》inception_v1.pytorch

inception_v1.pytorch

2020-01-09 | |  33 |   0 |   0

inception_v1.pytorch

An implementation of inception_v1 on pytorch with pretrained weights.

This code is a pytorch translation of the soumith torch repo: https://github.com/soumith/inception.torchIt implements the original version of the inception architechture; what is known has GoogLeNet.

Pretrained weights can be found at https://mega.nz/#!4RJE1SSY!kcCDyhkum6EQqVtqTc-deHnQuckM3zYSYq16bADbfww

Disclaimer

Test accuracy of the pretrained model on imagenet is only 26.38%. If I am not mistaken, this is an issue of the original torch repo - the data loading is done correctly. If you train this model to better accuracy, I would love to get the new set of weights!

License

The code is licensed under the MIT Licence. See the LICENSE file for detail.


上一篇：SqueezeNet-Residual

下一篇：DenseNet121-VHRRSI

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...