资源分类
》 资源 》算法》chainer-DenseNet

chainer-DenseNet

2019-09-19 | |  103 |   0 |   0

Densely Connected Convolutional Network implementation by Chainer

Implementation by Chainer. Original paper is Densely Connected Convolutional Network.

Requirements

Start training

For example, run,

python train.py --gpus 0 --batchsize 64 --dataset cifar10 --lr 0.1 --depth 100 --growth_rate 24 --split_size 4

Show possible options

python train.py --help

Sample results

  • Cifar-10 (batchsize=64, depth=100, growth_rate=24, with data augmentation)

Original paper reported 3.74% validation error under the same conditions.

  • Cifar-100 (batchsize=64, depth=100, growth_rate=24, with data augmentation)

Original paper reported 19.25% validation error under the same conditions.


上一篇：simple-fast-rnn

下一篇：Deep-Leafsnap

用户评价
全部评价

热门资源

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • tensorflow-sketch...

    Discrlaimer: This is not an official Google pro...

  • My_DrQA

    My_DrQA A re-implement DrQA based on Pytorch

  • ETD_cataloguing_a...

    ETD catalouging project using allennlp