Qingzhao Zhang
Qingzhao Zhang
Hi @juyangbai, the ADE (7.13) and FDE (17.83) is the error in l2 distance, which is in meter^2. The smaller numbers 2.69 and 5.39 are actually squared roots of ADE...
Hi @juyangbai, I double confirmed that I can use the formulated test data to reproduce the ADE/FDE number. Your code looks good to me though. I would guess the problem...
@juyangbai Thank you a lot. I see the problem now. First, I used the full nuScenes dataset along with the map all in v1.0. Second, according to your error report,...
Sorry for this very late reply. Unfortunately I lost the specific scripts over the years. Basically: xy_distribution is computed on the whole training set, calculating min/max/mean/std of x and y...
Sorry for not maintaining this repo for a long time. I train the models using dirty hardcodes in the original model repos, so sadly there is no clean scripts. However,...