I am studying GNN and trying to follow and study some code samples. What i am looking at is Detecting fraud in heterogeneous networks using Amazon SageMaker and Deep Graph Library | AWS Machine Learning Blog.
I am trying to implement this by plain python environment instead of amazon sagemaker. By following corresponding github repo, i have finished the data processing part to proceed to model training part. But when i start train the model, it just throw
MXNetError: Traceback (most recent call last): File “…/src/ndarray/ndarray.cc”, line 507 MXNetError: Check failed: delay_alloc:
I am doing it on paperspace gradient ML platform with A5000 machine while using CUDA 11.6 (Actually i am not using GPU yet). mxnet and dgl version are 1.9.1 and 1.0.2 correspondingly.
Anyone knows what potential reason to cause this?
I already tried to change the version of mxnet but it still not work.
