Spyke

Syndicated from the fediverse. Read and engage on the original instance.

View original on lemmy.sdf.org
mediocreatbestbymediocreatbest

[Paper] Optimizing Deep Learning Models For Raspberry Pi. Custom CNN (on MNIST data) performance from 114ms to 3.75ms. ResNet50 (on "flowers" data): from 1.1s to 1.0s (lowest) or 1.6s (highest).

I'm a little unsure on if I interpreted the results correctly. It seems like some things that TF Lite natively supports (apparently, their custom CNN model trained on MNIST) get really fast, and other things are a little hit-or-miss.

[Paper] Optimizing Deep Learning Models For Raspberry Pi. Custom CNN (on MNIST data) performance from 114ms to 3.75ms. ResNet50 (on "flowers" data): from 1.1s to 1.0s (lowest) or 1.6s (highest).https://arxiv.org/abs/2304.13039Open linkView original on lemmy.sdf.org
1
Comments

No replies yet

No comments on the original post yet.
[Paper] Optimizing Deep Learning Models For Raspberry Pi. Custom CNN (on MNIST data) performance from 114ms to 3.75ms. ResNet50 (on "flowers" data): from 1.1s to 1.0s (lowest) or 1.6s (highest). | Spyke