- 1.122.0 (latest)
- 1.121.0
- 1.120.0
- 1.119.0
- 1.118.0
- 1.117.0
- 1.116.0
- 1.115.0
- 1.114.0
- 1.113.0
- 1.112.0
- 1.111.0
- 1.110.0
- 1.109.0
- 1.108.0
- 1.107.0
- 1.106.0
- 1.105.0
- 1.104.0
- 1.103.0
- 1.102.0
- 1.101.0
- 1.100.0
- 1.99.0
- 1.98.0
- 1.97.0
- 1.96.0
- 1.95.1
- 1.94.0
- 1.93.1
- 1.92.0
- 1.91.0
- 1.90.0
- 1.89.0
- 1.88.0
- 1.87.0
- 1.86.0
- 1.85.0
- 1.84.0
- 1.83.0
- 1.82.0
- 1.81.0
- 1.80.0
- 1.79.0
- 1.78.0
- 1.77.0
- 1.76.0
- 1.75.0
- 1.74.0
- 1.73.0
- 1.72.0
- 1.71.1
- 1.70.0
- 1.69.0
- 1.68.0
- 1.67.1
- 1.66.0
- 1.65.0
- 1.63.0
- 1.62.0
- 1.60.0
- 1.59.0
- 1.58.0
- 1.57.0
- 1.56.0
- 1.55.0
- 1.54.1
- 1.53.0
- 1.52.0
- 1.51.0
- 1.50.0
- 1.49.0
- 1.48.0
- 1.47.0
- 1.46.0
- 1.45.0
- 1.44.0
- 1.43.0
- 1.39.0
- 1.38.1
- 1.37.0
- 1.36.4
- 1.35.0
- 1.34.0
- 1.33.1
- 1.32.0
- 1.31.1
- 1.30.1
- 1.29.0
- 1.28.1
- 1.27.1
- 1.26.1
- 1.25.0
- 1.24.1
- 1.23.0
- 1.22.1
- 1.21.0
- 1.20.0
- 1.19.1
- 1.18.3
- 1.17.1
- 1.16.1
- 1.15.1
- 1.14.0
- 1.13.1
- 1.12.1
- 1.11.0
- 1.10.0
- 1.9.0
- 1.8.1
- 1.7.1
- 1.6.2
- 1.5.0
- 1.4.3
- 1.3.0
- 1.2.0
- 1.1.1
- 1.0.1
- 0.9.0
- 0.8.0
- 0.7.1
- 0.6.0
- 0.5.1
- 0.4.0
- 0.3.1
Types for Google Cloud Aiplatform V1 Schema Predict Params v1 API
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.ImageClassificationPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Image Classification.
confidence_threshold()
The Model only returns predictions with atleast this confidence score. Default value is0.0
Type
max_predictions()
The Model only returns up to that many top,by confidence score, predictions per instance.If this number is very high, the Model mayreturn fewer predictions. Default value is 10.
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
max_predictions(: [int](https://python.readthedocs.io/en/latest/library/functions.html#int )
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.ImageObjectDetectionPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Image Object Detection.
confidence_threshold()
The Model only returns predictions with atleast this confidence score. Default value is0.0
Type
max_predictions()
The Model only returns up to that many top,by confidence score, predictions per instance.Note that number of returned predictions is alsolimited by metadata’s predictionsLimit. Defaultvalue is 10.
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
max_predictions(: [int](https://python.readthedocs.io/en/latest/library/functions.html#int )
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.ImageSegmentationPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Image Segmentation.
confidence_threshold()
When the model predicts category of pixels ofthe image, it will only provide predictions forpixels that it is at least this much confidentabout. All other pixels will be classified asbackground. Default value is 0.5.
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.VideoActionRecognitionPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Video Action Recognition.
confidence_threshold()
The Model only returns predictions with atleast this confidence score. Default value is0.0
Type
max_predictions()
The model only returns up to that many top,by confidence score, predictions per frame ofthe video. If this number is very high, theModel may return fewer predictions per frame.Default value is 50.
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
max_predictions(: [int](https://python.readthedocs.io/en/latest/library/functions.html#int )
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.VideoClassificationPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Video Classification.
confidence_threshold()
The Model only returns predictions with atleast this confidence score. Default value is0.0
Type
max_predictions()
The Model only returns up to that many top,by confidence score, predictions per instance.If this number is very high, the Model mayreturn fewer predictions. Default value is10,000.
Type
segment_classification()
Set to true to request segment-levelclassification. Vertex AI returns labels andtheir confidence scores for the entire timesegment of the video that user specified in theinput instance. Default value is true
Type
shot_classification()
Set to true to request shot-levelclassification. Vertex AI determines theboundaries for each camera shot in the entiretime segment of the video that user specified inthe input instance. Vertex AI then returnslabels and their confidence scores for eachdetected shot, along with the start and end timeof the shot.WARNING: Model evaluation is not done for thisclassification type, the quality of it dependson the training data, but there are no metricsprovided to describe that quality.Default value is false
Type
one_sec_interval_classification()
Set to true to request classification for avideo at one-second intervals. Vertex AI returnslabels and their confidence scores for eachsecond of the entire time segment of the videothat user specified in the input WARNING: Modelevaluation is not done for this classificationtype, the quality of it depends on the trainingdata, but there are no metrics provided todescribe that quality. Default value is false
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
max_predictions(: [int](https://python.readthedocs.io/en/latest/library/functions.html#int )
one_sec_interval_classification(: [bool](https://python.readthedocs.io/en/latest/library/functions.html#bool )
segment_classification(: [bool](https://python.readthedocs.io/en/latest/library/functions.html#bool )
shot_classification(: [bool](https://python.readthedocs.io/en/latest/library/functions.html#bool )
class google.cloud.aiplatform.v1.schema.predict.params_v1.types.VideoObjectTrackingPredictionParams(mapping=None, *, ignore_unknown_fields=False, **kwargs)
Bases:proto.message.Message
Prediction model parameters for Video Object Tracking.
confidence_threshold()
The Model only returns predictions with atleast this confidence score. Default value is0.0
Type
max_predictions()
The model only returns up to that many top,by confidence score, predictions per frame ofthe video. If this number is very high, theModel may return fewer predictions per frame.Default value is 50.
Type
min_bounding_box_size()
Only bounding boxes with shortest edge atleast that long as a relative value of videoframe size are returned. Default value is 0.0.
Type
confidence_threshold(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
max_predictions(: [int](https://python.readthedocs.io/en/latest/library/functions.html#int )
min_bounding_box_size(: [float](https://python.readthedocs.io/en/latest/library/functions.html#float )
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-10-30 UTC.