peterlipan / ASD_GP_GCN

ASD diagnosis on ABIDE I
MIT License
43 stars 10 forks source link

Accuracy problem #5

Open RRRRendy opened 10 months ago

RRRRendy commented 10 months ago

Great job! I used the commands

python download_ABIDE.py python main.py But I got the results:

GCN 10 fold test set results, loss = 0.691561, accuracy = 0.517241 GCN 10 fold val set results, loss = 0.632226, accuracy = 0.576923 Mean Accuracy: 0.522257

I haven't changed any parameters, and I would like to ask you if there might be other possible issues that are preventing me from replicating your results.

peterlipan commented 10 months ago

Hi! I'm sorry that this project is no longer being maintained, and I can hardly remember the implementation details. Maybe you can check the dataset (I am not sure if you can retrieve the same dataset using download_ABIDE.py), preprocessing, and running environments.

RRRRendy commented 10 months ago

Do you mean to say that your dataset was not obtained through 'python download_ABIDE.py'? May I have access to the data corresponding to your results?

RRRRendy commented 10 months ago

Can I access the dataset you use?

15265792229 commented 1 week ago

您好,这篇论文是否已经发表?