i think you should scale down the input shape from 227,227,3 to 32,32,3(because of cifar images shape). Also try reducing the size of kernels from (11,11) to (3,3) and stride to 1. y doing so you are preventing the details from getting missed out.Also you need to reduce th neurons of fc layers from 4096 to 1028.These are the basic steps you can do to get the model work. Even then there are a lot of steps involved to get your model reach decent accuracy.