Batches in LinkNeighborLoader do not show any content

[xubingze]

Hi everybody, I am trying to do LinkNeighborLoader after RandomLinkSplit of train, val and test data on Colab. Here are my codes:

import argparse
import os.path as osp
import time
import torch
import torch.nn.functional as F
from torch_geometric.loader import LinkNeighborLoader
import torch_geometric.transforms as T
from torch_geometric.datasets import Planetoid
from torch_geometric.logging import init_wandb, log
from torch_geometric.nn import GATConv
import random
import numpy as np

torch.cuda.empty_cache()
sn = 42
torch.manual_seed(sn)
np.random.seed(sn)
random.seed(sn)
torch.cuda.manual_seed_all(sn)

parser = argparse.ArgumentParser()
parser.add_argument('--dataset', type=str, default='Cora')
parser.add_argument('--hidden_channels', type=int, default=8)
parser.add_argument('--heads', type=int, default=8)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--epochs', type=int, default=200)
parser.add_argument('--wandb', action='store_true', help='Track experiment')
args = parser.parse_args(args=[])

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
init_wandb(name=f'GAT-{args.dataset}', heads=args.heads, epochs=args.epochs,
           hidden_channels=args.hidden_channels, lr=args.lr, device=device)

path = osp.join(osp.dirname(osp.realpath('PyGAT_Stocktwits.ipynb')), '..', 'data', 'Planetoid')
dataset = Planetoid(path, args.dataset, transform=T.NormalizeFeatures())
data = dataset[0].to(device)
split = T.RandomLinkSplit(
    num_val=0.05,
    num_test=0.1,
    is_undirected=True,
    add_negative_train_samples=False,
    neg_sampling_ratio=1.0,
)
train_data, val_data, test_data = split(data)


batch_size = 128
num_neighbors = -1
train_loader = LinkNeighborLoader(data = train_data,
                                  num_neighbors=num_neighbors,
                                  batch_size=batch_size,
                                  neg_sampling_ratio=1.0,
                                  shuffle=True)
val_loader = LinkNeighborLoader(data = val_data,
                                  num_neighbors=num_neighbors,
                                  batch_size=batch_size)
test_loader = LinkNeighborLoader(data = test_data,
                                  num_neighbors=num_neighbors,
                                  batch_size=batch_size)

print(train_loader)
for batch in train_loader:
    print(batch)

And I get this error, which I do not find from anywhere else.

Can someone help me with this issue?
Thank you very much in advance for your help.

[rusty1s]

Can you post your PyG and pyg-lib version?

[xubingze]

Okay, pyg_lib version is '0.3.1+pt21cu118'. Here is the codes:

!pip install pyg-lib -f https://data.pyg.org/whl/torch-2.1.0+cu118.html
import pyg_lib
pyg_lib.__version__

[xubingze]

Hi, can you help me with this issue? Thank you very much!

[rusty1s]

Thanks. I can reproduce this. Will fix shortly.

[rusty1s]

Looks like the fix is either than I thought. You need to specify num_neighbors as a list:

num_neighbors = [-1]

[xubingze]

Thank you very much! I made a silly mistake ( ꩜ ᯅ ꩜;) 
I will be more careful next time.