TransformersImageClassification

Basic image classification task

Subclass of Task.

Module: implementation.tasks

Default predictor

This task uses TransformersModel by default with this configuration:

model = AutoModelForImageClassification.from_pretrained(
    "facebook/deit-base-distilled-patch16-384"
)
predictor=TransformersModel(
    TransformersModelConfig(
        model=model
    ),
    input_class=TransformersImageModelInput,
    output_class=TransformersLogitsOutput,
)

See:

• TransformersModel

• TransformersModelConfig

• TransformersImageClassificationModelInput

• TransformersLogitsOutput

Methods and properties

Main methods and properties

---

__init__

Arguments:

• predictor (Predictor[Any, Any], optional): Predictor that will be used in task. If equals to None, default predictor will be used. Defaults to None.
• preprocess (Optional[Component], optional): Component executed before predictor. If equals to None, default component will be used. Defaults to None. Default component: ImagePad | ImageClassificationPreprocessor If default chain is used, ImageClassificationPreprocessor will use AutoImageProcessor from model used in predictor.
• postprocess (Optional[Component], optional): Component executed after predictor. If equals to None, default component will be used. Defaults to None. Default component: ImageClassificationSingleLabelPostprocessor If default chain is used, ImageClassificationSingleLabelPostprocessor will use labels from model used in predictor.
• input_class (Type[Input], optional): Class for input validation. Defaults to TransformersImageClassificationInput.
• output_class (Type[Output], optional): Class for output validation. Defaults to TransformersImageClassificationOutput.
• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

---

---

TransformersImageClassificationInput

Subclass of IOModel.

---

__init__

Arguments:

• image (Image.Image): Image to process.

---

---

---

TransformersImageClassificationOutput

Subclass of IOModel.

---

__init__

Arguments:

• label (Optional[Tuple[str, float]]): Classified label and score.

---

---

---

TransformersImageClassificationMultilabelOutput

Subclass of IOModel.

---

__init__

Arguments:

• labels (Dict[str, float]): Classified labels and scores.

---

---

---

ImageClassificationPreprocessor

Prepare model input. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• processor (Processor): Feature extractor.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "image" (Image.Image): Image to analyze;

Returns:

• Dict[str, Any]: Expected keys:

  • "pixel_values" (Any);

---

---

---

ImageClassificationSingleLabelPostprocessor

Process model output. Subclass of ImageClassificationMultilabelPostprocessor.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "logits" (Any): Model output;

Returns:

• Dict[str, Any]: Expected keys:

  • "label" (Optional[Tuple[str, float]]): Label with highest score, if score higher or equal to threshold, else - None.

---

---

---

ImageClassificationMultilabelPostprocessor

Process model output. Subclass of Action. Type of Action[Dict[str, Any], Dict[str, Any]].

---

__init__

Arguments:

• labels (Mapping[Any, str]): Labels for classification.

• threshold (float): Labels threshold score. Defaults to 0.

• name (Optional[str], optional): Name for identification. If equals to None, class name will be used. Defaults to None.

---

execute

Arguments:

• input_data (Dict[str, Any]): Expected keys:

  • "logits" (Any): Model output;

Returns:

• Dict[str, Any]: Expected keys:

  • "labels" (Dict[str, float]): Classified labels and scores.

---

---