ChengkaiYang

Thanks for your excellent work! In the following objective, the approximating posterior of the latent variable is p_old(z|y,x1:t).The paper has said it can be calculated because the latent variable z...

Problems about training

3

Hi,Doctor Zhou: Well done work!But I have some problems. 1.What causes the OOM problem during training?Recently,someone says that Argoverse2 dataset has different size of map representation input.When training,random combination of...

Dear Author, I noticed that in FDS.smooth code,there exists: "feature[labels == label] = self.calibrate_mean_var(feature[labels == label], ...)" Does the operation an inplace operation when backwards? features receive gradient from regressor...

Dear Author: I hope this issue finds you well! First of all, your work is constructive. When i apply your method to my work, i have found a puzzled phenomenon....

Hi @YyzHarry, I noticed your excellent work and want to apply to my own work. My work is a multi-modal work. That is to say my encoded features fuse multi-modal...

Questions about keypoints

1

Dear @cocoon2wong : What a great job in trajectory prediction! But I still have some questions. In AKL loss, we supervise coarse trajectory with keypoints. How do we get ground...