资源分类
》 资源 》算法》chainer-DenseNet

chainer-DenseNet

2020-03-30 | |  35 |   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)

图片.png

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

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

图片.png

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

上一篇：mnist-capsnet-api

下一篇：pytorch-densenet-tiramisu

用户评价
全部评价

热门资源

  • 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 ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...