basecls.models.vgg#
VGG Series
VGG: “Very Deep Convolutional Networks for Large-Scale Image Recognition”
- class basecls.models.vgg.VGGStage(w_in, w_out, depth, norm_name, act_name)[源代码]#
基类:
Module
VGG stage (sequence of blocks w/ the same output shape).
- class basecls.models.vgg.VGG(depths, widths, norm_name=None, act_name='relu', head=None)[源代码]#
基类:
Module
VGG model.
- 参数
depths (
Sequence
[int
]) – depth for each stage (number of blocks in the stage).widths (
Sequence
[int
]) – width for each stage (width of each block in the stage).norm_name (
Optional
[str
]) – normalization function. Default:None
act_name (
str
) – activation function. Default:"relu"
head (
Optional
[Mapping
[str
,Any
]]) – head args. Default:None