1 code implementation • 26 Jun 2021 • Zhiqiang Que, Erwei Wang, Umar Marikar, Eric Moreno, Jennifer Ngadiuba, Hamza Javed, Bartłomiej Borzyszkowski, Thea Aarrestad, Vladimir Loncar, Sioni Summers, Maurizio Pierini, Peter Y Cheung, Wayne Luk
The proposed approach has been evaluated based on two LSTM models, targeting a ZYNQ 7045 FPGA and a U250 FPGA.
The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training.
Research has shown that deep neural networks contain significant redundancy, and thus that high classification accuracy can be achieved even when weights and activations are quantized down to binary values.
Furthermore, we show how Tomato produces implementations of networks with various sizes running on single or multiple FPGAs.
Research has shown that deep neural networks contain significant redundancy, and that high classification accuracies can be achieved even when weights and activations are quantised down to binary values.
Deep neural networks have proven to be particularly effective in visual and audio recognition tasks.