Classify Images 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 Folder with the images to be used.
Select the File Consumer operator and enter the directory path where the images are stored.
Run the graph and open the Terminal UI.