Dominic Rüfenacht
Dominic Rüfenacht
@tangchen2 Have you used the pretrained weights for FaceNet, as they mention in the paper? Otherwise, the results are likely quite a bit worse if you are training only on...
Assuming that you are following the same training schedule (and sampling) as they report in the paper, it looks like there is some bug in your implementation. 60% is validation...
Another thing worth checking is that the order of the color channels that you input to FaceNet (RGB versus BGR).
Last (obvious) thing to check is that you are only considering what they refer to as "strong" triplets, i.e., the ones where at least 66% of the raters agree on....
@SkalskiP Note that including the ball into the radar view is tricky as it is not always on the ground and hence its location will be wrong for flying balls....