资源算法Deep Networks with Stochastic Depth

Deep Networks with Stochastic Depth

2019-09-17 | |  88 |   0 |   0

Deep Networks with Stochastic Depth

Keras implementation for "Deep Networks with Stochastic Depth" http://arxiv.org/abs/1603.09382

Original code is at https://github.com/yueatsprograms/Stochastic_Depth.

Usage

  1. Install Theano following its instruction.

  2. Install Keras (I use new API at keras-1 branch)

$ cd keras
$ git checkout keras-1
$ python setup.py install
  1. Just run python train.py

Known Issues

  • Error related to maximum recursion depth

    • When the network is deep, there happens error saying it reaches to maximum recursion depth.

    • You can resolve this issue by using sys.setrecursionlimit(max_recursion_depth). You should increase max_recursion_depth until you get no error (Increasing this value might cause segmentation fault if you don't have enough memory).

Results

  • Number of layers == 50

  • (other configs are same as train.py)

results


上一篇:FractalNet

下一篇:fmpytorch

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...