search

SYLan2019 / DSTAGNN

DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting, which is accepted at ICML2022.
129 stars 22 forks source link

generate dataset problem #5

Open zyd98123 opened 1 year ago

zyd98123 commented 1 year ago

Hello, author, first of all, thank you for your hard work. I have a question to ask you. This problem occurs when the stag_001 file is generated. How did you solve it? image

zyd98123 commented 1 year ago

When calculating wasserstein_distance, d[i, j] = spatial_temporal_similarity(data[:, :, i], data[:, :, j], normal=False, transpose=False), modify it to d[i, j] = spatial_temporal_similarity(data[:, :, i], data[:, :, j], normal=False, transpose=True), I would like to consult you on this question

hczs commented 5 months ago

Hello, author, first of all, thank you for your hard work. I have a question to ask you. This problem occurs when the stag_001 file is generated. How did you solve it? image

Hello, have you solved this problem? I also encountered the same error.