basecls.models.snet#
Shufflenet Series
ShufflenetV2: “ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design”
引用
megvii-model/ShuffleNet-Series
- class basecls.models.snet.SNV2Block(w_in, w_out, w_mid, *, kernel, stride, norm_name, act_name, se_r, drop_path_prob, **kwargs)[源代码]#
基类:
Module
ShuffleNet V2 Block
- class basecls.models.snet.SNV2XceptionBlock(w_in, w_out, w_mid, *, kernel, stride, norm_name, act_name, se_r, drop_path_prob, **kwargs)[源代码]#
基类:
SNV2Block
ShuffleNet V2 Xception stype block used in ShuffleNet V2+
- class basecls.models.snet.SNetV2(block, stem_w, depths, widths, strides, kernels, use_maxpool=True, se_r=0.0, drop_path_prob=0.0, norm_name='BN', act_name='relu', head=None)[源代码]#
基类:
Module
ShufflenetV2 model.
- 参数
block (
Callable
) – building block to use,SNV2XceptionBlock
for v2+.stem_w (
int
) – width for stem layer.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).strides (
Sequence
[int
]) – strides for each stage (applies to the first block of each stage).use_maxpool (
bool
) – whether use maxpool stride 2 after stem. Default:True
se_r (
float
) – Squeeze-and-Excitation (SE) ratio. Default:0.0
drop_path_prob (
float
) – drop path probability. Default:0.0
norm_name (
str
) – normalization function. Default:"BN"
act_name (
str
) – activation function. Default:"relu6"
head (
Optional
[Mapping
[str
,Any
]]) – head args. Default:None