Link Search Menu Expand Document

Object Classification

  1. Overview
  2. Object Classification MobileNet
    1. Inference Engine and Algorithm
    2. Running Object Classification
      1. Using Images for Inference
        1. Default Image
        2. Custom Image
      2. Using Video Source for Inference
        1. Video File
      3. Video Camera or Webcam
    3. Extra Parameters
  3. References

Overview

Object Classification is the problem of identifying to which of a set of categories a new observation belongs, on the basis of a training set of data containing observations whose category membership is known. Examples are assigning a given email to the “spam” or “non-spam” class, and assigning a diagnosis to a given patient based on observed characteristics of the patient 1 .

Object Classification MobileNet

Inference Engine and Algorithm

tfliteframework

This demo uses:

  • TensorFlow Lite as an inference engine 2 ;
  • MobileNet as default algorithm 3 .

More details on eIQ™ page.

Running Object Classification

Using Images for Inference

Default Image
  1. Run the Object Classification demo using the following line:
    # pyeiq --run object_classification_tflite
    
    • This runs inference on a default image: classification
Custom Image
  1. Pass any image as an argument:
    # pyeiq --run object_classification_tflite --image=/path_to_the_image
    

Using Video Source for Inference

Video File
  1. Run the Object Classification using the following line:
    # pyeiq --run object_classification_tflite --video_src=/path_to_the_video
    
    • This runs inference on a video file: classification_video

Video Camera or Webcam

  1. Specify the camera device:
    # pyeiq --run object_classification_tflite --video_src=/dev/video<index>
    

Extra Parameters

  1. Use –help argument to check all the available configurations:
    # pyeiq --run object_classification_tflite --help
    

References

  1. https://en.wikipedia.org/wiki/Statistical_classification 

  2. https://www.tensorflow.org/lite 

  3. https://arxiv.org/abs/1704.04861