Closed schirrmacher closed 3 months ago
Okay I found it out by myself here for the interested:
Here an inference with --input-size 518
:
Here an inference with --input-size 1036
:
So yes, the increase in inference input improves the quality! Great job!
In the paper you mentioned "test-time resolution scaling up images". I am not sure what this exactly means.
Can I just increase the resolution when performing inference by setting the input size here or is another training required?