biologically plausible neural networks

Pretrain lighter vision models

Recognizing the need for more accessible alternatives to large pretrained vision models on imagenet, this repo aims to provide models pretrained on smaller datasets like MNIST and CIFAR10. These lighter and more manageable models are pretrained for easy import and utilization, facilitating quick experimentation and integration into projects where resources are limited.

The MNIST database contains 60,000 training images and 10,000 testing images.

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

Learning rules

Neural networks

Evaluation

Reference:

1.PyTorch CIFAR10 by huyvnphan

2.https://en.wikipedia.org/wiki/MNIST_database

Except for torchvision models, GluonCV includes many sota models in CV.