Zhaonan Wang
Zhaonan Wang
Hi Ivan, thanks so much for your clarification. By "deteriorated trend", you mean the time series masked by artificial missing, right? Since I actually began implementing GAN for a similar...
Thanks for your interests. Since this repo means to be a PyTorch replication of the original model proposed in the paper, I do not have the exact dataset for you...
You can run the inflow_data by changing the seq_len as suggested by @wuhaiwanglei . And don't forget to change the corresponding model parameter in script Curb_GAN.py, as it has been...
Hi Zezhi, Thanks for the prompt response. Yes, that makes sense. I guess I am more interested in knowing the coordinates or IDs of the sensors. I found it for...
No worry at all. Thanks for letting me know.
Hello. Thanks for your interest in this repo. The shape of data actually represents OD (origin-destination) matrix - essentially (number-of-samples, number-of-origins, number-of-destinations). Supposing we have 47 regions, then the shape...
Hi again. You are right. I forgot to mention that here we expand the last dimension (to 1) to fit the input for the 2D graph convolution operation. Thus, you...