Image estimator

`TabPFNWithImages`

Fits an estimator on a frame whose declared image columns become features.

TabPFNWithImages(
    estimator: BaseEstimator,
    *,
    image_features_indices: Sequence[int],
    n_components: int = DEFAULT_N_COMPONENTS,
    batch_size: int = DEFAULT_BATCH_SIZE,
)

Parameters

Parameter	Type	Default	Description
`estimator`	`BaseEstimator`	Required	Typically a `TabPFNClassifier` or `TabPFNRegressor`; cloned at `fit`. Its `categorical_features_indices`, when set, are positions in the caller’s frame and are moved to the expanded frame. Its `device`, when it has one, is where the image encoder runs.
`image_features_indices`	`Sequence[int]`	Required	Positions in `X` whose cells hold images, each as a base64 string, as the image file’s path or bytes, or as a PIL image.
`n_components`	`int`	`DEFAULT_N_COMPONENTS`	Features an image column is expanded into.
`batch_size`	`int`	`DEFAULT_BATCH_SIZE`	Images per encoder forward pass.

Attributes

Attribute	Type	Description
`estimator_`	`Any`	The fitted clone of `estimator`.
`image_transformer_`	`ImageTransformer`	The fitted `ImageTransformer`.

`TabPFNWithImages.classes_`

View source

The fitted estimator’s classes; a classifier’s attribute only. Returns

Type	Description
`Any`	—

`TabPFNWithImages.fit`

View source

Expand the image columns of X, then fit a clone of the estimator.

TabPFNWithImages.fit(
    X: pd.DataFrame,
    y: Any,
    **fit_params: Any,
) -> TabPFNWithImages

Parameters

Parameter	Type	Default	Description
`X`	`pd.DataFrame`	Required	—
`y`	`Any`	Required	—
`**fit_params`	`Any`	—	—

Returns

Type	Description
`TabPFNWithImages`	—

`TabPFNWithImages.predict`

View source

The fitted estimator’s predict on the expanded X.

TabPFNWithImages.predict(
    X: pd.DataFrame,
    **predict_params: Any,
) -> Any

Parameters

Parameter	Type	Default	Description
`X`	`pd.DataFrame`	Required	—
`**predict_params`	`Any`	—	—

Returns

Type	Description
`Any`	—

`TabPFNWithImages.predict_proba`

View source

The fitted estimator’s predict_proba on the expanded X.

TabPFNWithImages.predict_proba(
    X: pd.DataFrame,
) -> Any

Parameters

Parameter	Type	Default	Description
`X`	`pd.DataFrame`	Required	—

Returns

Type	Description
`Any`	—

`TabPFNWithImages.score`

View source

The fitted estimator’s score on the expanded X.

TabPFNWithImages.score(
    X: pd.DataFrame,
    y: Any,
) -> Any

Parameters

Parameter	Type	Default	Description
`X`	`pd.DataFrame`	Required	—
`y`	`Any`	Required	—

Returns

Type	Description
`Any`	—

Reference

tabpfn

tabpfn-client

tabpfn-extensions

REST API

`TabPFNWithImages`

`TabPFNWithImages.classes_`

`TabPFNWithImages.fit`

`TabPFNWithImages.predict`

`TabPFNWithImages.predict_proba`

`TabPFNWithImages.score`

​TabPFNWithImages

​TabPFNWithImages.classes_

​TabPFNWithImages.fit

​TabPFNWithImages.predict

​TabPFNWithImages.predict_proba

​TabPFNWithImages.score

`TabPFNWithImages`

`TabPFNWithImages.classes_`

`TabPFNWithImages.fit`

`TabPFNWithImages.predict`

`TabPFNWithImages.predict_proba`

`TabPFNWithImages.score`