LinkNet

class mmit.decoders.LinkNet(input_channels, input_reductions, decoder_channel=32, upsample_layer=<class 'mmit.base.upsamplers.ConvTranspose2d'>, norm_layer=<class 'torch.nn.modules.batchnorm.BatchNorm2d'>, activation_layer=<class 'torch.nn.modules.activation.ReLU'>, extra_layer=<class 'torch.nn.modules.linear.Identity'>, mismatch_layer=<class 'mmit.base.mismatch.Pad'>)

Implementation of the Linknet decoder. Paper: https://arxiv.org/abs/1707.03718

Parameters:
  • input_channels (List[int]) – The channels of the input features.

  • input_reductions (List[int]) – The reduction factor of the input features.

  • decoder_channel (int) – The channel for the output of the decoder.

forward(*features)

Forward pass of the decoder.

Parameters:

*features (Tensor) – Features from the encoder, the first is the input image, last one the deepest.

property out_classes: int

Number of output classes.