LazyConv2d

class torch.nn.LazyConv2d(out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

A torch.nn.Conv2d module with lazy initialization of the in_channels argument.

The in_channels argument of the Conv2d that is inferred from the input.size(1). The attributes that will be lazily initialized are weight and bias.

Check the torch.nn.modules.lazy.LazyModuleMixin for further documentation on lazy modules and their limitations.

参数

• out_channels (int) – 卷积产生的通道数

• kernel_size (int or tuple) – Convolving kernel size

• stride (int or tuple, optional) – Convolution stride. Default: 1

• padding (int or tuple, optional) – Zero-padding added to both sides of the input. Default: 0

• dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1

• groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1

• bias (bool, optional) – If True, adds a learnable bias to the output. Default: True

• padding_mode (str, optional) – 'zeros', 'reflect', 'replicate' or 'circular'. Default: 'zeros'

另请参阅

torch.nn.Conv2d and torch.nn.modules.lazy.LazyModuleMixin

cls_to_become

alias of Conv2d