Bernard Lange
Bernard Lange
Hi @sb93, did you solve the issue?
Downgrading to tf 1.10 fixes it.
@zwqnju, have you succeeded at tuning the parameters for Nuscenes dataset?
Clarification on the above response, should we expect 2,030 independent segments, i.e. 2,030 20-second segments with sensor measurements at 10 Hz? I've loaded a v2 version of the dataset with...
First, track down where the NaNs originate. Either the input observations contain some NaNs, or the weights became NaN during training due to instability or NaNs in the loss function....
> By the way, will you upload the validation part, or how can i validate? I'll try to find the exact script I've used. Validation script just compares the FDE/ADE...