Prediction with Image File

Request Parameters

Name	Type	Description	Available Version
`modelId`	string	ID of the model that makes the prediction.	1.0
`numResults`	int	Number of probabilities to return. Optional. If passed, must be a number greater than zero. The response is sorted by `probability` in descending order. For example, if you pass in `3`, only the top three `label` and `probability` values are returned.	2.0
`sampleContent`	string	Binary content of image file uploaded as multipart/form-data.	1.0
`sampleId`	string	String that you can pass in to tag the prediction. Optional. Can be any value, and is returned in the response.	1.0

Keep the following points in mind when sending an image in for prediction:

The maximum image file size you can pass to this resource is 5 MB.
The supported image file types are PNG, JPG, and JPEG.
If you omit the numResults parameter and the modelId specifies a standard classification model, the response returns the top five labels and probabilities.
The numResults parameter has no effect on the response from a multi-label model. The prediction response from a multi-label model always returns probabilities for all the labels in a model.

Response Body

Name	Type	Description	Available Version
`message`	string	Error message. Returned only if the status is something other than successful (200).	1.0
`object`	string	Object returned; in this case, `predictresponse`.	1.0
`probabilities`	array	Array of probabilities for the prediction.	1.0
`sampleId`	string	Value passed in when the prediction call was made. Returned only if the `sampleId` request parameter is provided.	1.0
`status`	string	Status of the prediction. Status of 200 means the prediction was successful.	1.0

Probabilities Response Body

Name	Type	Description	Available Version
`label`	string	Probability label for the input.	1.0
`probability`	float	Probability value for the input. Values are between 0–1.	1.0

Probabilities from a Multi-Label Model

A multi-label model (modelType is image-multi-label) is designed to return predictions for multiple objects in an image. The response format is the same as a prediction from a model with a modelType of image, however, the probabilities don't add up to one.

For example, if you send an image of a baseball bat and a baseball glove into a sports-related multi-label model, the response might look something like the following JSON. This response shows high probabilities for both the baseball-bat and the baseball-glove labels.

{
  "probabilities": [
    {
      "label": "baseball-bat",
      "probability": 0.7356758
    },
    {
      "label": "baseball-glove",
      "probability": 0.74909562
    },
    {
      "label": "basketball-hoop",
      "probability": 0.112600096
    },
    {
      "label": "tennis-ball",
      "probability": 0.088070825
    },
    {
      "label": "tennis-racket",
      "probability": 0.0854089
    },
    {
      "label": "tennis-court",
      "probability": 0.0007318517
    }
  ],
  "object": "predictresponse"
}

When a response comes back from a multi-label model, it returns probabilities for all the labels in the model. Multi-label models are available in Einstein Vision API verison 2.0 and later.

Rate Limit Headers

Any time you make an API call to the /predict resource, your rate limit information is returned in the header. The rate limit headers specify your prediction usage for the current calendar month only.

X-RateLimit-Limit 2000
X-RateLimit-Remaining 1997
X-RateLimit-Reset 2017-04-01 19:31:42.0

Header	Description	Example
`X-RateLimit-Limit`	Maximum number of prediction calls available for the current plan month.	2000
`X-RateLimit-Remaining`	Total number of prediction calls you have left for the current plan month.	1997
`X-RateLimit-Reset`	Date on which your predictions are next provisioned. Always the first of the month.	2017-04-01 22:07:40.0