basecls.layers.modules

basecls.layers.modules.conv2d(w_in, w_out, k, *, stride=1, dilation=1, groups=1, bias=False)

Helper for building a conv2d layer.

It will calculate padding automatically.

参数

• w_in (int) – input width.

• w_out (int) – output width.

• k (int) – kernel size.

• stride (int) – stride. Default: 1

• dilation (int) – dilation. Default: 1

• groups (int) – groups. Default: 1

• bias (bool) – enable bias or not. Default: False

返回类型

Conv2d

返回

A conv2d module.

basecls.layers.modules.norm2d(name, w_in, **kwargs)

Helper for building a norm2d layer.

参数

• norm_name – normalization name, supports None, "BN", "GN", "IN", "LN" and "SyncBN".

• w_in (int) – input width.

返回类型

Module

返回

A norm2d module.

basecls.layers.modules.pool2d(k, *, stride=1, name='max')

Helper for building a pool2d layer.

参数

• k (int) – kernel size.

• stride (int) – stride. Default: 1

• name (str) – pooling name, supports "avg" and "max".

返回类型

Module

返回

A pool2d module.

basecls.layers.modules.gap2d(shape=1)

Helper for building a gap2d layer.

参数

shape – output shape. Default: 1

返回类型

AdaptiveAvgPool2d

返回

A gap2d module.

basecls.layers.modules.linear(w_in, w_out, *, bias=False)

Helper for building a linear layer.

参数

• w_in (int) – input width.

• w_out (int) – output width.

• bias (bool) – enable bias or not. Default: False

返回类型

Linear

返回

A linear module.

class basecls.layers.modules.SE(w_in, w_se, act_name, approx_sigmoid=False)

基类：Module

Squeeze-and-Excitation (SE) block: AvgPool, FC, Act, FC, Sigmoid.

参数

• w_in (int) – input width.

• w_se (int) – se width.

• act_name (str) – activation name.

• approx_sigmoid (bool) – approximated sigmoid function.

avg_pool

gad2d layer.

f_ex

sequantial which conbines conv2d -> act -> conv2d -> sigmoid.

forward(x)

返回类型

Tensor

class basecls.layers.modules.DropPath(drop_prob=0.0, **kwargs)

基类：Dropout

DropPath block.

参数

drop_prob – the probability to drop (set to zero) each path.

forward(x)