timm documentation

Models

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.9.16).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Models

timm.create_model

< >

( model_name: str pretrained: bool = False pretrained_cfg: Union = None pretrained_cfg_overlay: Optional = None checkpoint_path: str = '' scriptable: Optional = None exportable: Optional = None no_jit: Optional = None **kwargs )

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): Classifier dropout rate for training. drop_path_rate (float): Stochastic depth drop rate for training. global_pool (str): Classifier global pooling type.

Example:

>>> from timm import create_model

>>> # Create a MobileNetV3-Large model with no pretrained weights.
>>> model = create_model('mobilenetv3_large_100')

>>> # Create a MobileNetV3-Large model with pretrained weights.
>>> model = create_model('mobilenetv3_large_100', pretrained=True)
>>> model.num_classes
1000

>>> # Create a MobileNetV3-Large model with pretrained weights and a new head with 10 classes.
>>> model = create_model('mobilenetv3_large_100', pretrained=True, num_classes=10)
>>> model.num_classes
10

timm.list_models

< >

( filter: Union = '' module: str = '' pretrained: bool = False exclude_filters: Union = '' name_matches_cfg: bool = False include_tags: Optional = 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