Recently the idea of using deep learning algorithms in massive multiple-input multiple-output channel state information feedback has been studied in great detail. To use the deep-learning-based feedback schemes over the air, they must be able to operate under extremely large antennas. These schemes also need to be verified under a realistic channel model and propagation environment. Thus, we propose ChannelAttention, a deep-learning-based channel state information feedback scheme that utilizes attention layers and residual blocks. Simulations for a 64-by-64 QuaDRiGa channel model based on the 3GPP 38.901 urban microcell scenario show that ChannelAttention surpasses the normalized mean square error and cosine similarity performance of the conventional CsiNet+ scheme across all compression ratio ranges.