Open aofchas opened 1 year ago
@zhengsx
A littele update from my side. I modified the following part of the code to load my own dataset directly. https://github.com/microsoft/Graphormer/blob/77f436db46fb9013121289db670d1a763f264153/graphormer/tasks/graph_prediction.py#L161-L165 My dataset can be successfully loaded and trained. But the loss seems to be constant. I do not know whether the problem is related to the code that I changed. I am still working on it.
Hallo everone, I wanted to train a customized dataset. Following the instructions in https://graphormer.readthedocs.io/en/latest/Datasets.html#id5 I added my code before the create_customized_dataset function to build a dgl dataset class. Then I wrote a shell file to run the training process. But I got ModuleNotFoundError error when I started the training. Here was the error information
Here was the shell file
Anyone knows why it happens and maybe a solution for it? Thank you very much!