EncoderMixin

tiatoolbox . models . architecture . utils . EncoderMixin

class EncoderMixin

Mixin class adding encoder-specific functionality.

Initialize EncoderMixin defaults.

Methods

get_stages	Return encoder stages for dilation modification.
make_dilated	Convert encoder to a dilated version for segmentation.
set_in_channels	Change first convolution channels.

Attributes

out_channels	Return channels dimensions for each tensor of forward output of encoder.
output_stride	Return the effective output stride of the encoder.

get_stages()

Return encoder stages for dilation modification.

Return type:

dict[int, Sequence[torch.nn.Module]]

make_dilated(output_stride)

Convert encoder to a dilated version for segmentation.

Parameters:

output_stride (int)

Return type:

None

property out_channels: list[int]

Return channels dimensions for each tensor of forward output of encoder.

property output_stride: int

Return the effective output stride of the encoder.

set_in_channels(in_channels, *, pretrained=True)

Change first convolution channels.

Parameters:

• in_channels (int)

• pretrained (bool)

Return type:

None