Federated Learning brings the possibility to train visual models in a privacy-preserving way using real-world data on mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We also provide an improvement to the algorithm when its performance falls off. Experiments on the CIFAR-10 dataset show that such modifications lead to better learning on all setups. In highly skewed settings, we are able to improve performance up to 166%, achieving comparable results to traditional data-center learning in all but the most extreme cases.