Skip to content
a simple pytorch implement of Multi-Sample Dropout
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
png
README.md
nn.py
progressbar.py
run.py
tools.py
trainingmonitor.py

README.md

Multi-Sample Dropout PyTorch

This repository contains a PyTorch implementation of the Multi-Sample Dropout from the paper

Multi-Sample Dropout for Accelerated Trainingand Better Generalization

by Hiroshi Inoue.

model

Multi-Sample Dropout is a new way to expand the traditional Dropout by using multiple dropout masks for the same mini-batch.

Dependencies

  • PyTorch
  • torchvision

Uage

The code in this repository implements Multi-Sample Dropout training, with example on the CIFAR-10 datasets.

To use Multi-Sample Dropout use the following command.

python run.py --dropout_num = 8

Example

To experiment th result,we use CIFAR-10 dataset for MiniResNet.

# no dropout
python run.py --dropout_num=0

# sample = 1
python run.py --dropout_num=1

# sample = 8
python run.py --dropout_num=8

Results

Train loss of Multi-Sample Dropout with MiniResNet on CIFAR-10.

Valid loss of Multi-Sample Dropout with MiniResNet on CIFAR-10.

Valid accuracy of Multi-Sample Dropout with MiniResNet on CIFAR-10.

You can’t perform that action at this time.