You are tasked with developing a computer vision model to identify the type of government ID in images. For this, you utilize a GPU-powered virtual machine on Google Cloud's Compute Engine. The specific parameters for the model training are as follows: Optimizer: Stochastic Gradient Descent (SGD), Image shape: 224x224 pixels, Batch size: 64 images, Number of epochs: 10, Verbose level: 2. However, during the training process, you encounter an error message: ResourceExhaustedError: Out Of Memory (OOM) when allocating tensor. What should you do to resolve this issue?