Skip to content

Boolean Structured Convolutional Deep Learning Network (BSconvnet)

Notifications You must be signed in to change notification settings

singkuangtan/BSconvnet

Repository files navigation

Newly added

Pytorch BSconv layer class codes to substitute your ordinary conv layer. BSnet neurons can be substituted into convolution, fully connected, attention and transformer layers neurons.

BSconvnet

Boolean Structured Convolutional Deep Learning Network (BSconvnet)

Main Takeaways

  • Our model has only 17000+ parameters instead of 3.4 millions parameters in SmoothNet
  • Use separable convolutional deep learning network, so it does not overfit
  • Achieved state of the art accuracy on CIFAR10 dataset
  • Able to be trained on online using Google Colab with GPU
  • No data augmentations, no regularization such as weight decay and dropout

How to Run

Download the jupyter notebook

Open using Google Colab Colab It can also be run using a jupyter notebook

Follow the steps in the notebook, run each block of codes starting from the top to the bottom

Model

Network design Network design2

Experiment Results

Experiment results Experiment results2

Training set embeddings Test set embeddings

Leaderboard of model accuracies on CIFAR10 dataset Leaderboard

Leaderboard_pic

Links

BSnet paper link

BSautonet paper link

BSconvnet paper link

BSnet GitHub

Discrete Markov Random Field Relaxation

Slideshare

That's it. Have a Nice Day!!!

About

Boolean Structured Convolutional Deep Learning Network (BSconvnet)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published