sijieaaa
sijieaaa
Thanks for your reply! But it is still not clear to reproduce the results. Could you provide "train_pairs_10.pickle" and "test_items_10.pickle" that you used in your code? [https://github.com/MetaSLAM/AdaFusion/blob/b9f9b7abb1f53f98ea7333fb74383a0ffa6330c9/experiments/aavislidar3_pairwise/config.yaml#L22](url) Thanks!
> Dear @LiheYoung , > > First, thank you for sharing such a great work. The feature alignment technique to preserve semantic info is very interesting. I am very interested...
Thanks for your reply. 1. The issue is not caused by parallelization. Even with 1 process, if the generated codes contain any zombie part, the IDLE issue will show up,...