Upside down detector: Train a model to detect if images are upside down

• Trained on Google Street View.
• Synthetically turn some of images upside down. Create a training and test set.
• Build a neural network using TensorFlow.
• Train it to classify image orientation until a reasonable accuracy is reached.
• Look at some of the images that were classified incorrectly. Please explain what you might do to improve your model's performance on these images in the future.

The code is taken from: RotNet, with minor changes.