zhangpur

Hi, Thanks for your share of code. While calculating GAN loss, why do you consider to add a disturbance like uniform(0,7,1.2) or uniform(0,0.3) to the true/fake ground truth, instead of...

Visualization of trajectories

14

Since there are some questions about visualization, I've listed the solutions below. 1. Use the ORIGINAL data (trajectories in meters, which I've updated named with 'true_pos_origin.csv') and download videos from...

Why use two optimiziers?

2

Thanks for sharing this great work. I don't understand why introducing 'optimizer_2' for optimizing the complete trajectory decoder, could you give some directions? Thanks!

Hi! Sounds like shuffling between train/test split could cause lower prediction error. ` random_idx = random.sample(range(frame_num), frame_num)` `train_idx = random_idx[:int(frame_num * train_rate)]` `test_idx = random_idx[int(frame_num * train_rate):]` Is this setting...

Tracking results on NuScenes validation set

7

Thank you for sharing. Could you provide the tracking result file for the NuScenes validation set?