from fastai.gen_doc.nbdoc import *
from fastai.vision.models.darknet import Darknet
from fastai.vision.models.wrn import wrn_22, WideResNet
On top of the models offered by torchvision, the fastai library has implementations for the following models:
models.unetshow_doc(Darknet)
class Darknet[source][test]
Darknet(num_blocks:Collection[int],num_classes:int,nf=*32*) ::Module
No tests found for Darknet. To contribute a test please refer to this guide and this discussion.
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].
show_doc(WideResNet)
class WideResNet[source][test]
WideResNet(num_groups:int,N:int,num_classes:int,k:int=*1,drop_p:float=0.0,start_nf:int=16*) ::Module
No tests found for WideResNet. To contribute a test please refer to this guide and this discussion.
Wide ResNet with num_groups and a width of k.
Each 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.
show_doc(wrn_22)
wrn_22[source][test]
wrn_22()
No tests found for wrn_22. To contribute a test please refer to this guide and this discussion.
Wide ResNet with 22 layers.
This is a WideResNet with num_groups=3, N=3, k=6 and drop_p=0..