After inspecting the new data I realized that it could do with a bit of cleaning . Some images were taken between to frame and can have multiple target displayed which make them impossible to classify (even for a human) .
Being a bit lazy I decided to retrain the neural network without doing any data cleaning . It still managed to reach 75% accuracy . Not great but I believe that the 'uncleaned' data is probably the cause .

I was curious to see how it would perform on the nano so I loaded the model and starting feeding it the video feed from the camera . It didn't disappoint as it ran at around 25FPS!

My next move will be to clean the data and retrain the neural network one final time and get this thing to play its game!