Optimizing the performance of convolutional neural networks (CNNs) in real applications (i.e., production programs) is crucial. The desired network can perform a task while having minimal evaluation time and resource requirement. The evaluation time of a network strongly depends on the number of layers and the number of convolutional kernels in each layers. Therefore, by minimizing the network while keeping its accuracy high is a frequent task. In this paper, we present variations of a method for the automatic minimization of convolutional networks. Our method minimizes the neural network by omitting convolutional kernels during the training process, while also keeping the quality of the results high.