Open HRHLALALA opened 2 years ago
Hi, I found three potential bugs in src/utils/Trajectory_Dataloader:
src/utils/Trajectory_Dataloader
Bug 1 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L216 I think there is no +1 here otherwise it will start from index 1
+1
Bug 2 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L250 Here should be frameend_pedi = set(frameped_dict[cur_set][cur_frame + (self.args.seq_length-1) * skip[cur_set]])
frameend_pedi = set(frameped_dict[cur_set][cur_frame + (self.args.seq_length-1) * skip[cur_set]])
Bug 3 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L412 It seems like all position at (0,x) will be considered as missing which may drop several trajectories. I recommend to change the rule as np.nan
These bugs may result in fewer samples with full length being extracted than in Social GAN. One evidence is that when i add
if not iffull: continue
There are 24254 and 24334 full length samples (ped_cnt) extracted from UNIV test set before and after the modification.
ped_cnt
Hope this helps for further research if the total number of trajectories is sensitive to the results.
Hi, I found three potential bugs in
src/utils/Trajectory_Dataloader
:Bug 1 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L216 I think there is no
+1
here otherwise it will start from index 1Bug 2 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L250 Here should be
frameend_pedi = set(frameped_dict[cur_set][cur_frame + (self.args.seq_length-1) * skip[cur_set]])
Bug 3 https://github.com/Majiker/STAR/blob/d2dd113e3deb1098760c454ab15e7cb0652f3c0c/src/utils.py#L412 It seems like all position at (0,x) will be considered as missing which may drop several trajectories. I recommend to change the rule as np.nan
These bugs may result in fewer samples with full length being extracted than in Social GAN. One evidence is that when i add
There are 24254 and 24334 full length samples (
ped_cnt
) extracted from UNIV test set before and after the modification.Hope this helps for further research if the total number of trajectories is sensitive to the results.