Comparison of Performance of Optimized HSI CNN models on Desktop and Embedded Platforms

We compare different platforms for inference of convolutional neural networks in this paper. We trained various neural networks to determine the material in the source hyperspectral cube. Then we convert them to inference format and compare the inference results. We used tools under Xilinx Vitis AI for FPGA implementation. We try to minimize the size of the proposed networks by pruning them and provide further comparisons. FPGA platforms show to be energy efficient but still slower than a graphics card in terms of performance.