资源算法dynamic-routing-capsule-cifar

dynamic-routing-capsule-cifar

2020-01-15 | |  45 |   0 |   0

dynamic-routing-capsule-cifar

reference from : https://github.com/XifengGuo/CapsNet-Keras

Testing Cifar-10 datasets using Dynamic Routing between Capsules

This data will be compared with resnet18(18 layers deep) which contain a similar parameters with the tested capsule net in Hinton's paper.

Each epoch only takes less than 5 minutes in resnet, so I left it to train for over 100 epoch, which checkpoint stops at epoch 44Resnet

Each epoch in capsule net takes about 30 minutes, in this case, I only left it training for 60 epoch.Capsule

In the end, resnet yield an accuracy of 0.8231, while the "simple" capsule net only 0.7307

Here is the reconstruction result from the capsule decoder(3 fully connected layers). I suspect the bad reconstruction was due to simple FC network rather than using Image GAN structure of stacking Maxpooling(oops) and convolution layer. According to the paper, this addition reconstruction section contribute quite a significant increase in the final accuracy. In my opinion, it really doesn't makes sense, since the major study here was to evaluate the performance of capsule structure.

Reconstruction


上一篇:capsnet-traffic-sign-classifier

下一篇: pytorch-e2c

用户评价
全部评价

热门资源

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • mxnet_VanillaCNN

    This is a mxnet implementation of the Vanilla C...

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • Klukshu-Sockeye-...

    KLUKSHU SOCKEYE PROJECTS 2016 This repositor...