Hi,
Thank you for open-sourcing the code—this is truly amazing work!
I have a question regarding the single-image inference code in test.py. Specifically, I’m trying to understand the meaning of x, y, and z in this line. If x represents elevation change and y represents azimuth change, shouldn't it be:
[math.radians(0)], [math.radians(x)]
instead of:
[math.radians(90)], [math.radians(90+x)]
This would align with the implementation in the video inference version. (So is the results) Could you clarify if there’s a specific reason for adding 90 to x in this case?
Thank you for your help!
Hi,
Thank you for open-sourcing the code—this is truly amazing work!
I have a question regarding the single-image inference code in test.py. Specifically, I’m trying to understand the meaning of x, y, and z in this line. If x represents elevation change and y represents azimuth change, shouldn't it be:
[math.radians(0)], [math.radians(x)]
instead of:
[math.radians(90)], [math.radians(90+x)]
This would align with the implementation in the video inference version. (So is the results) Could you clarify if there’s a specific reason for adding 90 to x in this case?
Thank you for your help!