CoauthorshipCora dataset label error
Closed this issue · 1 comments
Sorry, my fault, I not noticed the target has been processed, please delete this issue.
#--------------------------------
Here is my code:
data = dhg.data.CoauthorshipCora()
print(data['labels'][data['train_mask']])
Print output as follow:
tensor([7, 4, 5, 1, 7, 5, 6, 4, 4, 4, 4, 2, 4, 2, 1, 3, 3, 5, 6, 6, 7, 1, 5, 4,
1, 7, 7, 7, 1, 7, 3, 1, 6, 6, 5, 7, 7, 1, 4, 6, 6, 1, 5, 6, 6, 4, 7, 3,
1, 3, 4, 5, 1, 1, 3, 3, 1, 3, 6, 3, 1, 5, 1, 5, 2, 7, 1, 1, 3, 3, 5, 5,
4, 7, 4, 1, 1, 1, 2, 1, 2, 1, 5, 6, 7, 4, 5, 4, 6, 3, 1, 6, 0, 7, 1, 4,
4, 1, 1, 6, 7, 7, 6, 5, 6, 1, 1, 4, 7, 1, 3, 7, 1, 1, 3, 1, 2, 4, 4, 0,
5, 6, 4, 6, 1, 5, 1, 7, 5, 1, 7, 2, 4, 1, 6, 4, 1, 3, 5, 6])
The labels has "7", it contains 0 to 7, but the data['num_classes'] is 7, the labels should be 0 to 6.
Please let me know if anything wrong.
Sorry, my fault, I not noticed the target has been processed, please delete this issue.