AutoModelForImageClassification

AutoModelForImageClassification

class transformers.AutoModelForImageClassification

<source>

( *args**kwargs )

This is a generic model class that will be instantiated as one of the model classes of the library (with a image classification head) when created with the from_pretrained() class method or the from_config() class method.

This class cannot be instantiated directly using __init__() (throws an error).

from_config

<source>

( **kwargs )

Parameters

• config (PretrainedConfig) — The model class to instantiate is selected based on the configuration class:

  • BeitConfig configuration class: BeitForImageClassification (BEiT model)

  • BitConfig configuration class: BitForImageClassification (BiT model)

  • ConvNextConfig configuration class: ConvNextForImageClassification (ConvNeXT model)

  • ConvNextV2Config configuration class: ConvNextV2ForImageClassification (ConvNeXTV2 model)

  • CvtConfig configuration class: CvtForImageClassification (CvT model)

  • Data2VecVisionConfig configuration class: Data2VecVisionForImageClassification (Data2VecVision model)

  • DeiTConfig configuration class: DeiTForImageClassification or DeiTForImageClassificationWithTeacher (DeiT model)

  • DinatConfig configuration class: DinatForImageClassification (DiNAT model)

  • Dinov2Config configuration class: Dinov2ForImageClassification (DINOv2 model)

  • EfficientFormerConfig configuration class: EfficientFormerForImageClassification or EfficientFormerForImageClassificationWithTeacher (EfficientFormer model)

  • EfficientNetConfig configuration class: EfficientNetForImageClassification (EfficientNet model)

  • FocalNetConfig configuration class: FocalNetForImageClassification (FocalNet model)

  • ImageGPTConfig configuration class: ImageGPTForImageClassification (ImageGPT model)

  • LevitConfig configuration class: LevitForImageClassification or LevitForImageClassificationWithTeacher (LeViT model)

  • MobileNetV1Config configuration class: MobileNetV1ForImageClassification (MobileNetV1 model)

  • MobileNetV2Config configuration class: MobileNetV2ForImageClassification (MobileNetV2 model)

  • MobileViTConfig configuration class: MobileViTForImageClassification (MobileViT model)

  • MobileViTV2Config configuration class: MobileViTV2ForImageClassification (MobileViTV2 model)

  • NatConfig configuration class: NatForImageClassification (NAT model)

  • PerceiverConfig configuration class: PerceiverForImageClassificationLearned or PerceiverForImageClassificationFourier or PerceiverForImageClassificationConvProcessing (Perceiver model)

  • PoolFormerConfig configuration class: PoolFormerForImageClassification (PoolFormer model)

  • PvtConfig configuration class: PvtForImageClassification (PVT model)

  • RegNetConfig configuration class: RegNetForImageClassification (RegNet model)

  • ResNetConfig configuration class: ResNetForImageClassification (ResNet model)

  • SegformerConfig configuration class: SegformerForImageClassification (SegFormer model)

  • SwiftFormerConfig configuration class: SwiftFormerForImageClassification (SwiftFormer model)

  • SwinConfig configuration class: SwinForImageClassification (Swin Transformer model)

  • Swinv2Config configuration class: Swinv2ForImageClassification (Swin Transformer V2 model)

  • VanConfig configuration class: VanForImageClassification (VAN model)

  • ViTConfig configuration class: ViTForImageClassification (ViT model)

  • ViTHybridConfig configuration class: ViTHybridForImageClassification (ViT Hybrid model)

  • ViTMSNConfig configuration class: ViTMSNForImageClassification (ViTMSN model)

Instantiates one of the model classes of the library (with a image classification head) from a configuration.

Note: Loading a model from its configuration file does not load the model weights. It only affects the model’s configuration. Use from_pretrained() to load the model weights.

Examples:

Copied

>>> from transformers import AutoConfig, AutoModelForImageClassification

>>> # Download configuration from huggingface.co and cache.
>>> config = AutoConfig.from_pretrained("bert-base-cased")
>>> model = AutoModelForImageClassification.from_config(config)

from_pretrained

<source>

( *model_args**kwargs )

Parameters

• pretrained_model_name_or_path (str or os.PathLike) — Can be either:

  • A string, the model id of a pretrained model hosted inside a model repo on huggingface.co. Valid model ids can be located at the root-level, like bert-base-uncased, or namespaced under a user or organization name, like dbmdz/bert-base-german-cased.

  • A path to a directory containing model weights saved using save_pretrained(), e.g., ./my_model_directory/.
  • A path or url to a tensorflow index checkpoint file (e.g, ./tf_model/model.ckpt.index). In this case, from_tf should be set to True and a configuration object should be provided as config argument. This loading path is slower than converting the TensorFlow checkpoint in a PyTorch model using the provided conversion scripts and loading the PyTorch model afterwards.

• model_args (additional positional arguments, optional) — Will be passed along to the underlying model __init__() method.

• config (PretrainedConfig, optional) — Configuration for the model to use instead of an automatically loaded configuration. Configuration can be automatically loaded when:

  • The model is a model provided by the library (loaded with the model id string of a pretrained model).

  • The model was saved using save_pretrained() and is reloaded by supplying the save directory.
  • The model is loaded by supplying a local directory as pretrained_model_name_or_path and a configuration JSON file named config.json is found in the directory.

• state_dict (Dict[str, torch.Tensor], optional) — A state dictionary to use instead of a state dictionary loaded from saved weights file.

  This option can be used if you want to create a model from a pretrained configuration but load your own weights. In this case though, you should check if using save_pretrained() and from_pretrained() is not a simpler option.
• cache_dir (str or os.PathLike, optional) — Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used.

• from_tf (bool, optional, defaults to False) — Load the model weights from a TensorFlow checkpoint save file (see docstring of pretrained_model_name_or_path argument).

• force_download (bool, optional, defaults to False) — Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist.

• resume_download (bool, optional, defaults to False) — Whether or not to delete incompletely received files. Will attempt to resume the download if such a file exists.

• proxies (Dict[str, str], optional) — A dictionary of proxy servers to use by protocol or endpoint, e.g., {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request.

• output_loading_info(bool, optional, defaults to False) — Whether ot not to also return a dictionary containing missing keys, unexpected keys and error messages.

• local_files_only(bool, optional, defaults to False) — Whether or not to only look at local files (e.g., not try downloading the model).

• revision (str, optional, defaults to "main") — The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so revision can be any identifier allowed by git.

• trust_remote_code (bool, optional, defaults to False) — Whether or not to allow for custom models defined on the Hub in their own modeling files. This option should only be set to True for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine.

• code_revision (str, optional, defaults to "main") — The specific revision to use for the code on the Hub, if the code leaves in a different repository than the rest of the model. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so revision can be any identifier allowed by git.

• kwargs (additional keyword arguments, optional) — Can be used to update the configuration object (after it being loaded) and initiate the model (e.g., output_attentions=True). Behaves differently depending on whether a config is provided or automatically loaded:

  • If a configuration is provided with config, **kwargs will be directly passed to the underlying model’s __init__ method (we assume all relevant updates to the configuration have already been done)

  • If a configuration is not provided, kwargs will be first passed to the configuration class initialization function (from_pretrained()). Each key of kwargs that corresponds to a configuration attribute will be used to override said attribute with the supplied kwargs value. Remaining keys that do not correspond to any configuration attribute will be passed to the underlying model’s __init__ function.

Instantiate one of the model classes of the library (with a image classification head) from a pretrained model.

The model class to instantiate is selected based on the model_type property of the config object (either passed as an argument or loaded from pretrained_model_name_or_path if possible), or when it’s missing, by falling back to using pattern matching on pretrained_model_name_or_path:

• beit — BeitForImageClassification (BEiT model)
• bit — BitForImageClassification (BiT model)
• convnext — ConvNextForImageClassification (ConvNeXT model)
• convnextv2 — ConvNextV2ForImageClassification (ConvNeXTV2 model)
• cvt — CvtForImageClassification (CvT model)
• data2vec-vision — Data2VecVisionForImageClassification (Data2VecVision model)
• deit — DeiTForImageClassification or DeiTForImageClassificationWithTeacher (DeiT model)
• dinat — DinatForImageClassification (DiNAT model)
• dinov2 — Dinov2ForImageClassification (DINOv2 model)
• efficientformer — EfficientFormerForImageClassification or EfficientFormerForImageClassificationWithTeacher (EfficientFormer model)
• efficientnet — EfficientNetForImageClassification (EfficientNet model)
• focalnet — FocalNetForImageClassification (FocalNet model)
• imagegpt — ImageGPTForImageClassification (ImageGPT model)
• levit — LevitForImageClassification or LevitForImageClassificationWithTeacher (LeViT model)
• mobilenet_v1 — MobileNetV1ForImageClassification (MobileNetV1 model)
• mobilenet_v2 — MobileNetV2ForImageClassification (MobileNetV2 model)
• mobilevit — MobileViTForImageClassification (MobileViT model)
• mobilevitv2 — MobileViTV2ForImageClassification (MobileViTV2 model)
• nat — NatForImageClassification (NAT model)
• perceiver — PerceiverForImageClassificationLearned or PerceiverForImageClassificationFourier or PerceiverForImageClassificationConvProcessing (Perceiver model)
• poolformer — PoolFormerForImageClassification (PoolFormer model)
• pvt — PvtForImageClassification (PVT model)
• regnet — RegNetForImageClassification (RegNet model)
• resnet — ResNetForImageClassification (ResNet model)
• segformer — SegformerForImageClassification (SegFormer model)
• swiftformer — SwiftFormerForImageClassification (SwiftFormer model)
• swin — SwinForImageClassification (Swin Transformer model)
• swinv2 — Swinv2ForImageClassification (Swin Transformer V2 model)
• van — VanForImageClassification (VAN model)
• vit — ViTForImageClassification (ViT model)
• vit_hybrid — ViTHybridForImageClassification (ViT Hybrid model)
• vit_msn — ViTMSNForImageClassification (ViTMSN model)

The model is set in evaluation mode by default using model.eval() (so for instance, dropout modules are deactivated). To train the model, you should first set it back in training mode with model.train()

Examples:

Copied

>>> from transformers import AutoConfig, AutoModelForImageClassification

>>> # Download model and configuration from huggingface.co and cache.
>>> model = AutoModelForImageClassification.from_pretrained("bert-base-cased")

>>> # Update configuration during loading
>>> model = AutoModelForImageClassification.from_pretrained("bert-base-cased", output_attentions=True)
>>> model.config.output_attentions
True

>>> # Loading from a TF checkpoint file instead of a PyTorch model (slower)
>>> config = AutoConfig.from_pretrained("./tf_model/bert_tf_model_config.json")
>>> model = AutoModelForImageClassification.from_pretrained(
...     "./tf_model/bert_tf_checkpoint.ckpt.index", from_tf=True, config=config
... )