Normalize input in object detector example

[Corallo]

Description

Hello, I took a look at your object detector example here That uses SSD mobilenetv2 (among the suggested parameters) from the coral page.

Looking with Netron at the network, I see that the input of the network is called: normalized_input_image_tensor. Does that mean that the network expect the input to be quantized somehow? If yes, is the normalization missing in the example?

Click to expand!

Issue Type

Documentation Bug

Operating System

Linux

Coral Device

No response

Other Devices

No response

Programming Language

Python 3.9

Relevant Log Output

No response

[hjonnala]

Hello @Corallo I think normalization and quantization not required for the detection demo. Feel free to add the code from classify_image.py if you wish to do so. Thanks!

[google-coral-bot[bot]]

Are you satisfied with the resolution of your issue? Yes No