Reason for multiplying 0.3 with the min depth and number of depth labels
txrc opened this issue · comments
Clement Tan commented
Hi, what's the reason for doing args.nlabel*args.mindepth*0.3
instead of just args.nlabel*args.mindepth
? I tried and I notice the difference, but am not sure what's the explanation for the depth map which looks better when it is multiplied with 0.3.
ynma-hanvo commented
hi, what value is suitable for mindepth , how to determine it with custom dataset inference