bitorch.models.densenet.DenseNet¶
- class bitorch.models.densenet.DenseNet(num_layers: Optional[int], input_shape: List[int], num_classes: int = 0, num_init_features: int = 64, growth_rate: int = 64, bn_size: int = 0, dropout: float = 0, dilated: bool = False, flex_block_config: Optional[List[int]] = None)[source]¶
Methods
Initializes internal Module state, shared by both nn.Module and ScriptModule.
allows additions to the argument parser if required, e.g.
Attributes
densenet_spec
name
- __init__(num_layers: Optional[int], input_shape: List[int], num_classes: int = 0, num_init_features: int = 64, growth_rate: int = 64, bn_size: int = 0, dropout: float = 0, dilated: bool = False, flex_block_config: Optional[List[int]] = None) None [source]¶
Initializes internal Module state, shared by both nn.Module and ScriptModule.
- static add_argparse_arguments(parser: ArgumentParser) None [source]¶
allows additions to the argument parser if required, e.g. to add layer count, etc.
! please note that the inferred variable names of additional cli arguments are passed as keyword arguments to the constructor of this class !
- Parameters:
parser (ArgumentParser) – the argument parser