How to test On-device latency?
Closed this issue · 1 comments
vokkko commented
It's a nice work for SR quantization. I have a question that how can i test the model latency on different device? Could you please provide some details for inference time ?
Cheeun commented
Dear @vokkko, I am sorry for such a delayed response.
To measure the latency on CPU, I used torch.quantization library.
Please refer to this tutorial for details, I followed it directly for my implementation.
I will include the latency measurement feature in this repo in the future.
Please stay tuned! Thanks for your attention!