What are the official optimization operations when using mobilenet-v2 network training on edge impulse to make the size of the generated model so small?
dansitu
September 15, 2021, 5:41pm
#3
Good question! I’ve posted a detailed outline in this other thread:
Hi @mengmeng ,
Great questions! Here’s exactly what we do:
We start with a base architecture designed for efficiency—the MobileNets are a good example of these.
We modify the width and depth of the architecture to make it smaller. For MobileNet models the width is expressed as alpha, which represents a fraction of the original model width—so our 0.35 model is 35% of the original model width.
We train the model as normal.
We then use post-training quantization to quantize the model (we’ll soon …
Warmly,
Dan
2 Likes