- class composer.models.ResNetHparams(initializers=<factory>, num_classes=None, model_name='', weights=None, pretrained=False, groups=1, width_per_group=64, loss_name='soft_cross_entropy')#
model_name (str) – Name of the ResNet model instance. Either [
num_classes (int, optional) – The number of classes. Needed for classification tasks. Default:
weights (str, optional) – If provided, pretrained weights can be specified, such as with
pretrained (bool, optional) – If True, use ImageNet pretrained weights. Default:
False. This parameter is deprecated and will soon be removed.
groups (int, optional) – Number of filter groups for the 3x3 convolution layer in bottleneck blocks. Default:
width_per_group (int, optional) – Initial width for each convolution group. Width doubles after each stage. Default:
initializers (List[Initializer], optional) – Initializers for the model.
Nonefor no initialization. Default: