What

This is an example of using model trained with Tensorflow in Unity application for image classification. It's a quick port of TF Classify example from Tensorflow repo, using TensorflowSharp for gluing it all together.

How

You'll need Unity 2017.1 or above and Unity Tensorflow Plugin.

• Open the project in Unity.
• Install Tensorflow plugin.
• Open Scene1 in Assets folder.
• In Edit -> Player Settings -> Other settings add ENABLE_TENSORFLOW to the Scripting Define Symbols for the target platform.
• In Other settings also set Scripting runtime version to Experimental (.NET 4.6 Equivalent).
• Build and run.

More info can be found here.

Notes

I'm neither Unity nor Tensorflow expert, so if you found any problems with this example feel free to open an issue.