victor000000
Results
3
comments of
victor000000
> hi, Mr. Bai. I got a very low performance while reproducing Transfusion-L. mAP:0.2484, NDS:0.2350. I only have a 8G NVIDIA 2080. And I trained on nuscenes-mini. I have searched...
131042 * 8(int64) = 1M 131042 *1024 * 8 = 1G
I found that in build_sknw(ske, multi=False, iso=True, ring=True) if ske is of type np.uint8, then if node num > 255 - 10, node_num will be 0, that is a bug...