Frequently Asked Questions
AURA - SmartEye

Common questions and responses of AURA Smart Eye.

  • Yes, In fact, SmartEye supports exporting annotations in all standard formats

  • Yes, SmartEye supports Image Classification, Object Detection, and Image Segmentation

  • There are multiple options,

    1. Export in TensorFlow / Pytorch’s standard saved model format
    2. Export as tf-serving docker image with http/grpc endpoints to serve.

  • SmartEye supports three types of data integration

    1. Direct data upload from local
    2. Cloud/Edge storage path mount for large datasets.
    3. Using public URL of video/Images
    2nd option is helpful with large media files.

  • Smart labeling is where the pre-trained or base model helps to annotate the dataset prior to human annotation. The base model is the one we create with a small labeled dataset by using transfer learning.