quancore / social-lstm

Social LSTM implementation in PyTorch
424 stars 255 forks source link

how to cover my pixel coordinates into such coordinates to train my model #28

Open hushunda opened 4 years ago

hushunda commented 4 years ago

the data is [frame id y x]. 0 5 -1.59 0.93 10 5 -1.59 0.93 20 5 -1.59 0.93 30 5 -1.59 0.93 40 5 -1.59 0.93 50 5 -1.59 0.93 60 5 -1.59 0.93 70 5 -1.59 0.93 80 5 -1.59 0.93 90 5 -1.59 0.93 100 5 -1.59 0.93

but i don't know the x-y coordinates represent?

quancore commented 4 years ago

Detailed info about challenge and datasets: https://www.aicrowd.com/challenges/trajnet-a-trajectory-forecasting-challenge

The creation of the dataset and each coordinate has been explained on the dataset section in the link.

ChinaWangYu666 commented 4 years ago

In your code, you calculate the value of x - y as relative coordinates, I don't understand the meaning of the x - y?