gcn
gcn copied to clipboard
tkipf
run GCN on my own dataset
Hi there is on things I want to ask . It can be a dumb question as I am new to it.
I want to run GCN on my own dataset. Is there any guide/steps how can I create my x,y,tx,ty,graph files from my own dataset ? what are the columns involved in these files etc.
I am focusing both supervised and unsupervised learning patterns.
Duplicate of https://github.com/tkipf/gcn/issues/113
On Wed, May 8, 2019 at 8:04 PM aubutt [email protected] wrote:
Hi there is on things I want to ask . It can be a dumb question as I am new to it.
I want to run GCN on my own dataset. Is there any guide/steps how can I create my x,y,tx,ty,graph files from my own dataset ? what are the columns involved in these files etc.
I am focusing both supervised and unsupervised learning patterns.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/tkipf/gcn/issues/114, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYERNYXSQA7NMIK4CHTPUMIZNANCNFSM4HLT6ADA .
sorry to border you , i read the answer in 113, i still have a confusion.
- Is there have another code that can create the file like x/tx/graph?
- On the other hand , i have the data about node, edge , how can i convert them to a type of data that can be used directly in code like "ind.citeseer.allx". Is there another code used here?
Have a look at https://github.com/tkipf/pygcn/blob/master/pygcn/utils.py#L15 for a more instructive example for how to create your own data loader.
On Wed, May 29, 2019 at 11:41 PM tiredDi [email protected] wrote:
sorry to border you , i read the answer in 113, i still have a confusion.
- Is there have another code that can create the file like x/tx/graph?
- On the other hand , i have the data about node, edge , how can i convert them to a type of data that can be used directly in code like "ind.citeseer.allx". Is there another code used here?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/tkipf/gcn/issues/114?email_source=notifications&email_token=ABYBYYCSQF6BUI3RSVU77VLPX5ZKNA5CNFSM4HLT6ADKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODWRQLVI#issuecomment-497223125, or mute the thread https://github.com/notifications/unsubscribe-auth/ABYBYYBLZNKJKMMUGYEBIKTPX5ZKNANCNFSM4HLT6ADA .