search

google-coral / pycoral

Python API for ML inferencing and transfer-learning on Coral devices
https://coral.ai
Apache License 2.0
347 stars 144 forks source link

Normalize input in object detector example #93

Closed Corallo closed 1 year ago

Corallo commented 1 year ago

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 commented 1 year ago

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] commented 1 year ago

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