I want to run the AI Benchmark Nightly app on a remote device.
The remote device is a Snapdragon 888.
I want to run a custom TfLite model on the app, using the .apk file, but I do not have access to the GUI of the device.
Is there a way to specify the custom model and other required parameters...
I was looking at the ranking available on your website-
https://ai-benchmark.com/ranking_detailed.html and observed that on
Snapdragon 888 for multiple models, NNAPI shows better latency numbers
compared to CPU for both int and float models.
Recently, I tested some DL models on Snapdragon 888...