TimmHparams

class composer.models.TimmHparams(initializers=<factory>, num_classes=1000, model_name=None, pretrained=False, drop_rate=0.0, drop_path_rate=None, drop_block_rate=None, global_pool=None, bn_momentum=None, bn_eps=None)

YAHP interface for composer_timm().

Parameters

• model_name (str) – timm model name e.g: "resnet50". List of models can be found at PyTorch Image Models.

• pretrained (bool, optional) – Imagenet pretrained. Default: False.

• num_classes (int, optional) – The number of classes. Needed for classification tasks. Default: 1000.

• drop_rate (float, optional) – Dropout rate. Default: 0.0.

• drop_path_rate (float, optional) – Drop path rate (model default if None). Default: None.

• drop_block_rate (float, optional) – Drop block rate (model default if None). Default: None.

• global_pool (str, optional) – Global pool type, one of ("fast", "avg", "max", "avgmax", "avgmaxc"). Model default if None. Default: None.

• bn_momentum (float, optional) – BatchNorm momentum override (model default if not None). Default: None.

• bn_eps (float, optional) – BatchNorm epsilon override (model default if None). Default: None.