Description

I would like to use OpenVINO as part of my AWS Lambda function in order to load and execute inference with models (packaged in .xml and .bin files) trained by OpenVINO framework.

Problem is, OpenVINO R1 that I am using takes ~900MB. My question is, what parts of OpenVINO do I need in order to load mode

Snapchat has a fullscreen camera and the resulting image when saved from snapchat to camera roll is still fullscreen like so:

However when using resizeAspectFill in

to help with unit tests, be able to turn off the text on the patterns. This will provide known image for testing inputs, testing loopback, and testing outputs (like the encoder).

I can see a case for leaving some of it on, but I would prefer the option of having the same image across all everythings. The case for testing for text on an image doesn't seem worth the effort in providing a UI/A