ResidualBlock

tiatoolbox . models . architecture . hovernet . ResidualBlock

class ResidualBlock(in_ch, unit_ksizes, unit_chs, unit_count, stride=1)

Residual block.

References

He, Kaiming, et al. “Deep residual learning for image recognition.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

Initialize ResidualBlock.

Methods

forward

Logic for using layers defined in init.

Attributes

training

Parameters:

• in_ch (int)

• unit_ksizes (list[int])

• unit_chs (list[int])

• unit_count (int)

• stride (int)

forward(prev_feat)

Logic for using layers defined in init.

Parameters:

• self (ResidualBlock)

• prev_feat (Tensor)

Return type:

Sequential