ValueError: row index 1708 out of bounds

HazyResearch / hgcn

Hyperbolic Graph Convolutional Networks in PyTorch.

602 stars 109 forks source link

ValueError: row index 1708 out of bounds #20

Closed NewXericHorizon closed 4 years ago

NewXericHorizon commented 4 years ago

Hi, I was faced with the problem by running the command "python train.py --task lp --dataset cora --model HGCN --lr 0.01 --dim 16 --num-layers 2 --act relu --bias 1 --dropout 0.5 --weight-decay 0.001 --manifold PoincareBall --log-freq 5 --cuda 0 --c None"

NewXericHorizon commented 4 years ago

I'm puzzled with the bug, could anyone solve the case? Much appreciation.

NewXericHorizon commented 4 years ago

I tried to debug it for about 4 hrs... I really tried to do so, but unfortunately I failed.

NewXericHorizon commented 4 years ago

@ines-chami Thanks a lot~

NewXericHorizon commented 4 years ago

Besides, the error only emerges when running cora and pubmed(ValueError: row index 18717 out of bounds) datasets. The airport and disease datasets could be used swiftly.