MobileNetConfig¶

class lucid.models.MobileNetConfig(width_multiplier: float = 1.0, num_classes: int = 1000, in_channels: int = 3)¶

MobileNetConfig stores the MobileNet-v1 settings used by lucid.models.MobileNet. It captures the width multiplier together with the classifier size and input channel count.

Class Signature¶

@dataclass
class MobileNetConfig:
    width_multiplier: float = 1.0
    num_classes: int = 1000
    in_channels: int = 3

Parameters¶

width_multiplier (float): Width scaling factor applied to each MobileNet-v1 channel dimension.
num_classes (int): Number of output classes.
in_channels (int): Number of channels in the input image tensor.

Validation¶

width_multiplier, num_classes, and in_channels must be greater than 0.

Usage¶

import lucid.models as models

config = models.MobileNetConfig(width_multiplier=0.75, num_classes=10, in_channels=1)
model = models.MobileNet(config)