Overview of the models used for CV in fastai

Computer Vision models zoo

On top of the models offered by torchvision, the fastai library has implementations for the following models:

  • Darknet architecture, which is the base of Yolo v3
  • Unet architecture based on a pretrained model. The original unet is described here, the model implementation is detailed in models.unet
  • Wide resnets architectures, as introduced in this article.

class Darknet[source]

Darknet(`num_blocks`:Collection[int], `num_classes`:int, `nf`=`32`) :: Module

https://github.com/pjreddie/darknet

Create a Darknet with blocks of sizes given in num_blocks, ending with num_classes and using nf initial features. Darknet53 uses num_blocks = [1,2,8,8,4].

class WideResNet[source]

WideResNet(`num_groups`:int, `N`:int, `num_classes`:int, `k`:int=`1`, `drop_p`:float=`0.0`, `start_nf`:int=`16`) :: Module

Wide ResNet with num_groups and a width of k.

Eeach group contains blocks of size N. start_nf the initial number of features. Dropout of drop_p is applied at the end of each block.

wrn_22[source]

wrn_22()

Wide ResNet with 22 layers.

This is a WideResNet with num_groups=3, N=3, k=6 and drop_p=0..