- class mmcv.ops.SAConv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, use_deform=False)¶
SAC (Switchable Atrous Convolution)
This is an implementation of DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution.
in_channels (int) – Number of channels in the input image
out_channels (int) – Number of channels produced by the convolution
padding_mode (string, optional) –
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:
use_deform – If
True, replace convolution with deformable convolution. Default:
Defines the computation performed at every call.
Should be overridden by all subclasses.
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.