Models

timm.create_model

( model_name: str pretrained: bool = False pretrained_cfg: typing.Union[str, typing.Dict[str, typing.Any], timm.models._pretrained.PretrainedCfg, NoneType] = None pretrained_cfg_overlay: typing.Union[typing.Dict[str, typing.Any], NoneType] = None checkpoint_path: str = '' scriptable: typing.Optional[bool] = None exportable: typing.Optional[bool] = None no_jit: typing.Optional[bool] = None **kwargs )

Parameters

model_name (str) — name of model to instantiate
pretrained (bool) — load pretrained ImageNet-1k weights if true
pretrained_cfg (Union[str, dict, PretrainedCfg]) — pass in external pretrained_cfg for model
pretrained_cfg_overlay (dict) — replace key-values in base pretrained_cfg with these
checkpoint_path (str) — path of checkpoint to load after the model is initialized
scriptable (bool) — set layer config so that model is jit scriptable (not working for all models yet)
exportable (bool) — set layer config so that model is traceable / ONNX exportable (not fully impl/obeyed yet)
no_jit (bool) — set layer config so that model doesn’t utilize jit scripted layers (so far activations only)

Create a model

Lookup model’s entrypoint function and pass relevant args to create a new model.

**kwargs will be passed through entrypoint fn to timm.models.build_model_with_cfg() and then the model class init(). kwargs values set to None are pruned before passing.

Keyword Args: drop_rate (float): dropout rate for training (default: 0.0) global_pool (str): global pool type (default: ‘avg’) **: other kwargs are consumed by builder or model init()

timm.list_models

< source >

( filter: typing.Union[str, typing.List[str]] = '' module: str = '' pretrained: bool = False exclude_filters: typing.Union[str, typing.List[str]] = '' name_matches_cfg: bool = False include_tags: typing.Optional[bool] = None )

Parameters

filter - Wildcard filter string that works with fnmatch —
module - Limit model selection to a specific submodule (ie ‘vision_transformer’) —
pretrained - Include only models with valid pretrained weights if True —
exclude_filters - Wildcard filters to exclude models after including them with filter —
name_matches_cfg - Include only models w/ model_name matching default_cfg name (excludes some aliases) —
include_tags - Include pretrained tags in model names (model.tag). If None, defaults — set to True when pretrained=True else False (default: None)

Return list of available model names, sorted alphabetically

Example: model_list(‘gluon_resnet’) — returns all models starting with ‘gluon_resnet’ model_list(’resnext*, ‘resnet’) — returns all models with ‘resnext’ in ‘resnet’ module