A new publication was recently accepted in the Sensors Journal:
Tragoudaras, A., Stoikos, P., Fanaras, K., Tziouvaras, A., Floros, G., Dimitriou, G., Kolomvatsos, K., Stamoulis, G., ‘Design Space Exploration of a Sparse MobileNetV2 Using High-Level Synthesis and Sparse Matrix Techniques on FPGAs’, Sensors, 22, 4318, 2022, https://doi.org/10.3390/s22124318.
The paper discusses the adoption of a MobileNetV2 model using a state-of-the-art High-Level
Synthesis (HLS) tool in order to conduct a design space exploration and provide insights on complex hardware designs which are tailored for the Deep Neural Network (DNN) inference.