Figure 8
From: A processing-in-pixel-in-memory paradigm for resource-constrained TinyML applications
Comparison of normalized total, sensing, and SoC (a) energy cost and (b) delay between the P2M, and baseline models architectures (compressed C, and non-compressed NC). Note, the normalization of each component was done by diving the corresponding energy (delay) value with the maximum total energy (delay) value of the three components.
