Glaucoma is an ocular disease that causes damage to the eye's optic nerve and successive narrowing of the visual field in affected patients which can lead the patient, in advanced stage, to blindness. This work presents a study on the use of Convolutional Neural Networks (CNNs) for the automatic diagnosis through eye fundus images. However, building a perfect CNN involves a lot of effort that in many situations is not always able to achieve satisfactory results. The objective of this work is to use a Genetic Algorithm (GA) to optimize CNNs architectures through evolution that can helps in glaucoma diagnosis using eye's fundus image from RIM-ONE-r2 dataset. Our partial results demonstrate satisfactory results after training the best individual chosen by GA with the achievement of an accuracy of 91%.