If you are building a robot driven by Raspberry Pi and want to use image recognition and object detection you may want to look into Googles Mobile Nets platform which lets you do use a several mobile-first computer vision models for TensorFlow, combined with an Intel Movidius Neural Compute Stick on a Rasrberry PI 3. The MobileNets platform is designed to be run on resource conservative devices while maintaining accuracy and the latter will give you an order of magnitude more compute power than running the detection on the raspberrys CPU.
Here you go. The Tensorflow 2017 Dev Summit.
https://github.com/vahidk/EffectiveTensorflow Attempts to demystify Tensorflow and provide some guidelines and best practices for more effective use of Tensorflow.