modelzoo.vision.pytorch.unet.layers.UNetBlock.UNetBlock#
- class modelzoo.vision.pytorch.unet.layers.UNetBlock.UNetBlock[source]#
Bases:
torch.nn.Module- Parameters
in_channels (int) – The input channel dimension before passing through the block.
out_channels (int) – The output channel dimension after passing through the block.
encoder (bool) – Flag if the block is part of the encoder section of the model. Returns the block-output if True, and a tuple of block-output, block-output before downsampling if False.
convs_per_block ([str]) – List of conv specifications for each conv in the block.
bias (bool) – Flag to use bias vectors.
norm_layer (nn.Module) – Desired normalization layer.
norm_kwargs (dict) – A dictionary of the arguments to pass to the constructor of the normalization layer.
act (str) – Activation to use.
skip_connect (bool) – Flag for if the model concatenates encoder outputs to decoder inputs.
residual_blocks (bool) – Flag for using residual connections.
downscale_method (str) – Downscaling method at the end of the block.
Methods
forward- __call__(*args: Any, **kwargs: Any) Any#
Call self as a function.
- __init__(in_channels, out_channels, encoder, convs_per_block, bias, norm_layer, norm_kwargs, act='relu', skip_connect=True, residual_blocks=False, downscale_method='max_pool', use_conv3d=False, downscale_first_conv=False, downscale=True)[source]#
- static __new__(cls, *args: Any, **kwargs: Any) Any#