Training weights file for the model

[guoyage]

Thanks to the author for his wonderful research. I am currently reproducing the performance of the model on the NGSIM data set, but the results of my training are larger than those shown in your paper. Can you provide the training weights you used to Would it be convenient for us to reproduce the evaluation results in your paper? Thank you, very much looking forward to your reply.

[Petrichor625]

Thanks for your interest in our work!

Our research was done on a separate server, and the uploaded code is an early version. Unfortunately, we can't provide the latest training weights at the moment. Your patience is appreciated as we work to update with the latest content. Please note that differences in training results may be due to unit discrepancies. RMSE calculations include proper unit conversions (feet to meters) for fair comparison. Printed results during training are in feet for efficiency, while test data is converted to meters for consistency. Testing on the validation set will demonstrate the final results. You may need to run tests on the validation set to get the final results. (Also, there may have been inaccuracies in the earlier version of the data set that we'll be correcting in the future).