Skip to content

The Randomly Wired Neural Network Pytorch Implementation

Notifications You must be signed in to change notification settings

JarvisLee0423/RandWiredNN_Model

Repository files navigation

RandWiredNN_Model

The Randomly Wired Neural Network Pytorch Implementation

For training the model demo one:

When training with the CIFAR10 dataset, please download the dataset from the link: https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz

Then uncompressed the data into the file named CIFAR10.

For environments setting:

pip install --user -r requirements.txt

For Training:

python Trainer.py -lr [LearningRate] -momentum [momentum] -wd [WeightDecay] -smoothing [LabelSmoothingRegularization] -channels [StandardChannels] -bs [BatchSize] -cs [ClassSize] -ep [Epoches] -seed [RandomSeed] -gpu [GPUID] -ggm [RandomGraphGeneratingMethod] -gt [RandomGraphType] -nodes [Nodes] -initialNode [BAParam] -e [BAParam] -k [WSParam] -p [WS/ERParam] -graphDir [GraphDir] -modelDir [ModelDir] -logDir [LogDir] -dataDir [DatasetsDir]

About

The Randomly Wired Neural Network Pytorch Implementation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages