Tensor size mismatch error when dynamic options are used about seal_ogb HOT 5 OPEN

Hi! It seems it is loading a previously saved model checkpoint. Did you use "--continue_from" and load a previously saved in-memory trained model in the dynamic mode? The dynamic mode will only use the first 1000 training graphs to estimate the $k$ used in SortPooling of DGCNN (see this line), which might result in different $k$ thus different dense dimension before the first linear layer. You can maually set $k$ to your previously obtained $k$ in in-memory mode.

from seal_ogb.

Thanks for your response Muhan.
No, I'm not using "--continue_from" when running the seal_link_pred.py script. These are all options that I'm using for running it in dynamic mode:
--dataset --num_hops --use_feature --use_edge_weight --epochs --num_workers --runs --dynamic_train --dynamic_val --dynamic_test --train_percent --pathdir

from seal_ogb.

Then can you show more lines near line 708 of your seal_link_pred.py file? I'd like to know what line 708's model.load_state_dict(torch.load(model_name)) is doing in order to debug.

from seal_ogb.

Yes, sure. These are lines 693-709:

from seal_ogb.

Thanks. The lines show that you are loading a previously saved model checkpoint. Did you train your model using in-memory mode and here load it in dynamic mode? My previous points are still valid, i.e., the gap causes their used $k$ to be different.

from seal_ogb.