Towards the on-device Handwriting Trajectory Reconstruction of the Sensor Enhanced Pen
Résumé
Performing handwriting trajectory regression from inertial data using Deep Neural Network (DNN) on an embedded device is a very challenging task, since the network accuracy is prone to imperfections in the weights and needs a significant amount of parameters to be able to regress. In this work, we apply and compare different quantization techniques and Mitchell logarithmic multiplication approximation in order to enable the on-device inference. We show that it is possible to perform the inference of the TCN-based regression model using only 8-bit fixed-point quantization without significant reconstruction precision loss and that the accuracy degradation of the approximate multiplication can be partially compensated with Quantizationaware Training (QAT). Finally, we demonstrate that the compressed models can be integrated into an off-the-shelf commercial Systems-on-Chip with minimal use of FPU and requiring only 460 KB of the ROM size for the TCN-49 configuration.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
