A backbone is a model used for feature extraction for higher level computer vision tasks such as object detection and image classification. Transformers provides an AutoBackbone class for initializing a Transformers backbone from pretrained model weights, and two utility classes:
timm models are loaded with the TimmBackbone and TimmBackboneConfig classes.
Backbones are supported for the following models:
( *args **kwargs )
BackboneMixin class transformers.utils.BackboneMixin < source >( )
Serializes this instance to a Python dictionary. Override the default to_dict() from PretrainedConfig to include the out_features and out_indices attributes.
( )
A Mixin to support handling the out_features and out_indices attributes for the backbone configurations.
Serializes this instance to a Python dictionary. Override the default to_dict() from PretrainedConfig to include the out_features and out_indices attributes.
( config **kwargs )
Wrapper class for timm models to be used as backbones. This enables using the timm models interchangeably with the other models in the library keeping the same API.
TimmBackboneConfig class transformers.TimmBackboneConfig < source >( backbone = None num_channels = 3 features_only = True use_pretrained_backbone = True out_indices = None freeze_batch_norm_2d = False **kwargs )
Parameters
str, optional) — The timm checkpoint to load. int, optional, defaults to 3) — The number of input channels. bool, optional, defaults to True) — Whether to output only the features or also the logits. bool, optional, defaults to True) — Whether to use a pretrained backbone. List[int], optional) — If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). Will default to the last stage if unset. bool, optional, defaults to False) — Converts all BatchNorm2d and SyncBatchNorm layers of provided module into FrozenBatchNorm2d. This is the configuration class to store the configuration for a timm backbone TimmBackbone.
It is used to instantiate a timm backbone model according to the specified arguments, defining the model.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> from transformers import TimmBackboneConfig, TimmBackbone
>>>
>>> configuration = TimmBackboneConfig("resnet50")
>>>
>>> model = TimmBackbone(configuration)
>>>
>>> configuration = model.config< > Update on GitHub
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.3