资源分类
》 资源 》算法》mixup.pytorch

mixup.pytorch

2020-02-04 | |  42 |   0 |   0

mixup.pytorch

An implementation of mixup: Beyond Empirical Risk Minimization by Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz.

python main.py [--batch_size 128 --epochs 400 --steps 250 300 --dataset cifar10 --model resnet20 --alpha 1 [--baseline]]

Requirements

  • PyTorch v1.0

  • torchvision (v0.2.2)

  • homura pip install -U git+https://github.com/moskoumule/homura (Use dev!)

Results

CIFAR10 on ResNet-20


EMPmixup
max. test accuracy92%93%


上一篇：benchmark_sgcn_pytorch

下一篇：pytorch-faster-rcnn-mixup

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...