Index
ImageClassificationPredictionInstance
(message)ImageObjectDetectionPredictionInstance
(message)ImageSegmentationPredictionInstance
(message)TextClassificationPredictionInstance
(message)TextExtractionPredictionInstance
(message)TextSentimentPredictionInstance
(message)VideoActionRecognitionPredictionInstance
(message)VideoClassificationPredictionInstance
(message)VideoObjectTrackingPredictionInstance
(message)
ImageClassificationPredictionInstance
Prediction input format for Image Classification.
content
string
The image bytes or Cloud Storage URI to make the prediction on.
mime_type
string
The MIME type of the content of the image. Only the images in below listed MIME types are supported. - image/jpeg - image/gif - image/png - image/webp - image/bmp - image/tiff - image/vnd.microsoft.icon
ImageObjectDetectionPredictionInstance
Prediction input format for Image Object Detection.
content
string
The image bytes or Cloud Storage URI to make the prediction on.
mime_type
string
The MIME type of the content of the image. Only the images in below listed MIME types are supported. - image/jpeg - image/gif - image/png - image/webp - image/bmp - image/tiff - image/vnd.microsoft.icon
ImageSegmentationPredictionInstance
Prediction input format for Image Segmentation.
content
string
The image bytes to make the predictions on.
mime_type
string
The MIME type of the content of the image. Only the images in below listed MIME types are supported. - image/jpeg - image/png
TextClassificationPredictionInstance
Prediction input format for Text Classification.
content
string
The text snippet to make the predictions on.
mime_type
string
The MIME type of the text snippet. The supported MIME types are listed below. - text/plain
TextExtractionPredictionInstance
Prediction input format for Text Extraction.
content
string
The text snippet to make the predictions on.
mime_type
string
The MIME type of the text snippet. The supported MIME types are listed below. - text/plain
key
string
This field is only used for batch prediction. If a key is provided, the batch prediction result will by mapped to this key. If omitted, then the batch prediction result will contain the entire input instance. Vertex AI will not check if keys in the request are duplicates, so it is up to the caller to ensure the keys are unique.
TextSentimentPredictionInstance
Prediction input format for Text Sentiment.
content
string
The text snippet to make the predictions on.
mime_type
string
The MIME type of the text snippet. The supported MIME types are listed below. - text/plain
VideoActionRecognitionPredictionInstance
Prediction input format for Video Action Recognition.
content
string
The Google Cloud Storage location of the video on which to perform the prediction.
mime_type
string
The MIME type of the content of the video. Only the following are supported: video/mp4 video/avi video/quicktime
time_segment_start
string
The beginning, inclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision.
time_segment_end
string
The end, exclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision, and "inf" or "Infinity" is allowed, which means the end of the video.
VideoClassificationPredictionInstance
Prediction input format for Video Classification.
content
string
The Google Cloud Storage location of the video on which to perform the prediction.
mime_type
string
The MIME type of the content of the video. Only the following are supported: video/mp4 video/avi video/quicktime
time_segment_start
string
The beginning, inclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision.
time_segment_end
string
The end, exclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision, and "inf" or "Infinity" is allowed, which means the end of the video.
VideoObjectTrackingPredictionInstance
Prediction input format for Video Object Tracking.
content
string
The Google Cloud Storage location of the video on which to perform the prediction.
mime_type
string
The MIME type of the content of the video. Only the following are supported: video/mp4 video/avi video/quicktime
time_segment_start
string
The beginning, inclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision.
time_segment_end
string
The end, exclusive, of the video's time segment on which to perform the prediction. Expressed as a number of seconds as measured from the start of the video, with "s" appended at the end. Fractions are allowed, up to a microsecond precision, and "inf" or "Infinity" is allowed, which means the end of the video.