Skip to content

Simple implementation of a residually connected convolutional neural network in PyTorch

License

Notifications You must be signed in to change notification settings

sagarreddypatil/cifar10-pytorch-cnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CIFAR 10 CNN in PyTorch

Performance

Test Accuracy: 87.31% Train Accuracy: 99.92%

How to run

python main.py

Info

The model uses residual connections between the start and end of each Convolutional block. However, partial residual connections have not been implemented for blocks with different input and output size.

Required Packages

  • pytorch
  • torchvision
  • tensorboard
  • scikit-learn
  • numpy
  • tqdm

About

Simple implementation of a residually connected convolutional neural network in PyTorch

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages