Image Classifier + Saliency: MobileNet

A state-of-the-art machine learning model that classifies images into one of 1,000 categories. These categories include a variety of animals, plants, and everyday objects. Also includes a saliency map to show the visual attention of the model.

Dataset Description: This model was trained on more than a million images from the ImageNet database. Compared to other ImageNet models, less data augmentation was used as the MobileNet is a smaller model.

Input
Output

View API [+][-]

POST /api/predict/26

Request
{
  data : string - A base64 string representation of the image to upload as input.
}

Response
{
  label : string - Most likely classification predicted by model.
  confidences : array (optional) - [{
    label : string - Classification for which confidence interval is being provided.
    confidence : number - Likelihood of classification as predicted by model.
  }]
}