We comment on a paper describing an algorithm for image set classification. Following the general practice in computer vision research, the performance of the algorithm was evaluated on benchmarks in order to support the claim of its advantage over other algorithms in the literature. We have examined the reported data of experiences on two datasets, and found that many numbers are not a possible answer regardless how the random partitions were selected and regardless how the algorithms performed in each partition. Our finding suggests that the experimental results in the paper ("Deep Reconstruction Models for Image Set Classification", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 37, no. 4, pp. 713-727, April 2015) has serious flaws to the extent that all the experimental results should be re-examined.