Closed peiyunh closed 4 years ago
Closing this issue as b.velocity
are no longer NaNs once I properly installed the customized nuscenes.
the author use the their fork version of nuscens-devkit. you can just modify this file ~/.local/lib/python3.6/site-packages/nuscenes/nuscenes.py
# Cannot estimate velocity for a single annotation.
if not has_prev and not has_next:
return np.array([0.0, 0.0, 0.0])
if time_diff > max_time_diff:
# If time_diff is too big, don't return an estimate.
return np.array([0.0, 0.0, 0.0])
else:
return pos_diff / time_diff
Interesting. Thanks for pointing this out!
Closing this issue as
b.velocity
are no longer NaNs once I properly installed the customized nuscenes.
Hi, I have both official and customized nuscenes devkit installed. How do you make sure that the customized version is used?
I think the easiest way is to create a virtual environment with only the customized devkit installed.
I believe this is related to #6 #42 #43 and #19 .
I followed INSTALL.md and installed nuscenes from https://github.com/poodarchu/nuscenes.git. I have also run
create_data.py
accordingly. From what I have seen, ground truth velocities that are cached ininfos_train_10sweeps_withvelo.pkl
are all NaN. I believe this is at least one of the issues that results in NaN losses.I think line 516 in
nusc_common.py
should be:
Otherwise the function (
box_velocity
) that computes velocity will never be called andb.velocity
will stay uninitialized as NaNs.