Classify Video Stream with Inception

This graph applies the inception neuronal network on any image that is fed into the input stream.

The graph can be separated into three main components:

Stream generation: The file consumer reads an image directory and feeds the image file names into the classify operator.
Inference: The classification operator applies the inception model on each image and streams the results into the output pipeline.
Output pipeline: The results of the classification are fed into a terminal, which displays them.

Prerequisites

(Only if run in local mode) Operators in this graph use the following libraries:
- Python 2.7+
- TensorFlow 1.7.0
- SciPy 1.0+ & Pillow 5.0+

Configure and Run the Graph

Follow the steps below to run the training example from the Data Pipeline UI:

Have a video that can be used.
Select the File Consumer operator and enter the directory path where the video is stored.
Run the graph and open the UI operator.
If the video is not running after the download is over, refresh the UI page.