Package prediction_v1.types (1.0.1)

Prediction output format for Image and Text Classification. .. attribute:: ids

The resource IDs of the AnnotationSpecs that had been identified, ordered by the confidence score descendingly.

:type: Sequence[int]

Prediction output format for Image Object Detection. .. attribute:: ids

The resource IDs of the AnnotationSpecs that had been identified, ordered by the confidence score descendingly.

:type: Sequence[int]

Prediction output format for Image Segmentation. .. attribute:: category_mask

A PNG image where each pixel in the mask represents the category in which the pixel in the original image was predicted to belong to. The size of this image will be the same as the original image. The mapping between the AnntoationSpec and the color can be found in model's metadata. The model will choose the most likely category and if none of the categories reach the confidence threshold, the pixel will be marked as background.

:type: str

Prediction output format for Tabular Classification. .. attribute:: classes

The name of the classes being classified, contains all possible values of the target column.

:type: Sequence[str]

Prediction output format for Tabular Regression. .. attribute:: value

The regression value.

:type: float

Prediction output format for Text Extraction. .. attribute:: ids

The resource IDs of the AnnotationSpecs that had been identified, ordered by the confidence score descendingly.

:type: Sequence[int]

Prediction output format for Text Sentiment .. attribute:: sentiment

The integer sentiment labels between 0 (inclusive) and sentimentMax label (inclusive), while 0 maps to the least positive sentiment and sentimentMax maps to the most positive one. The higher the score is, the more positive the sentiment in the text snippet is. Note: sentimentMax is an integer value between 1 (inclusive) and 10 (inclusive).

:type: int

Prediction output format for Video Action Recognition. .. attribute:: id

The resource ID of the AnnotationSpec that had been identified.

:type: str

Prediction output format for Video Classification. .. attribute:: id

The resource ID of the AnnotationSpec that had been identified.

:type: str

Prediction output format for Video Object Tracking. .. attribute:: id

The resource ID of the AnnotationSpec that had been identified.

:type: str