xincoder

@poojitharamachandra Thank you for adapting our work in solving other problems. Back to your question, we do not use any specific design to avoid colliding. There are two simple ways...

Hi @poojitharamachandra , thank you for your interesting in our work. 1. Please refer to the GRIP/xin_feeder_baidu.py (function __getitem__, line59) for the details of our data augmentation. Durining training, we...

@poojitharamachandra The velocities are calculated in main.py [line 99]. Thanks.

@jhtao1860 why do you say the loss is not decreasing. The logging file shows the details of each batch. If you plot the mean loss of each epoch (average all...

Hi @lzx-buaa , thank you so much for your interest in my work. 1. The code you mentioned (xin_feeder_baidu.py line64-79) is data augmentation only for training (if statement line64). The...

Hi jmin0530, first thank you for your interest in our work and your valuable questions. 1. the "hop_step" is used in GRIP/layers/graph.py [line 21], np.linalg.matrix_power(A, d). In Graph Theory, adjacency...

@jmin0530 Thank you for your interest and questions. These questions are easy to be figured out if you carefully read through our code. 1. "kc" is the name of a...

@Bigtuo. The first 6 numbers are ADE (not exactly implemented the metric as the website/paper description, considering the numerical stability problem), and the last number is the sum of the...

> Thank you. > > [Test_Epoch20] All_All: 0.275 0.498 0.739 1.011 1.289 1.584 5.397 > and then what does these values mean? Hi @han1222, thank you for your interest in...

Hi @jhtao1860 , thank you for your interest in our work and run it on your side. I did not face this problem before. There are several things that we...