Run Example - Githubissues

❓ Questions and Help

from openhgnn.dataset import generate_random_hg
from dgl import transforms as T
from dgl import DGLHeteroGraph
from dgl.data import DGLDataset
import torch as th
import numpy as np
import scipy.sparse as sp

category = 'p'
meta_paths_dict = {'pap': [('p', 'to', 'a'), ('a', 'to', 'p')]}

class MyNCDataset(DGLDataset):
    def __init__(self):
        super().__init__(name='my-nc-dataset')

    def process(self):
        # Generate a random heterogeneous graph with labels on target node type.
        self._g = load_acm()
        transform = T.Compose([T.ToSimple(), T.AddReverse()])
        # self._g = transform(self._g)

    # Some models require meta paths, you can set meta path dict for this dataset.
    @property
    def meta_paths_dict(self):
        return meta_paths_dict

    def __getitem__(self, idx):
        return self._g

    def __len__(self):
        return 1

def load_acm():
    path = "../data/acm/"
    ratio = [1, 5, 10, 20]
    label = np.load(path + "labels.npy").astype('int32')
    nei_a = np.load(path + "nei_a.npy", allow_pickle=True)
    nei_s = np.load(path + "nei_s.npy", allow_pickle=True)
    feat_p = sp.load_npz(path + "p_feat.npz").astype("float32")
    feat_a = sp.load_npz(path + "a_feat.npz").astype("float32")
    feat_s = make_sparse_eye(60)
    pap = sp.load_npz(path + "pap.npz")
    psp = sp.load_npz(path + "psp.npz")
    pos = sp.load_npz(path + "pos.npz")

    label = torch.LongTensor(label)
    nei_a = nei_to_edge_index([torch.LongTensor(i) for i in nei_a])
    nei_s = nei_to_edge_index([torch.LongTensor(i) for i in nei_s])
    feat_p = preprocess_sp_features(feat_p)
    feat_a = preprocess_sp_features(feat_a)
    feat_s = preprocess_th_features(feat_s)
    pap = sp_adj_to_tensor(pap)
    psp = sp_adj_to_tensor(psp)
    pos = sp_adj_to_tensor(pos)
    # nei_a size: (2, 13407)
    edge = {
        ('a', 'to', 'p'): (nei_a.flip([0])[0], nei_a.flip([0])[1]),
        ('s', 'to', 'p'): (nei_s.flip([0])[0], nei_s.flip([0])[1])
    }
    g = dgl.heterograph(edge)
    g.nodes['p'].data['x'] = feat_p
    g.nodes['s'].data['x'] = feat_s
    g.nodes['a'].data['x'] = feat_a
    g.nodes['p'].data['label'] = label

    # data[('p', 'a', 'p')].edge_index = pap
    # data[('p', 's', 'p')].edge_index = psp
    # data[('p', 'pos', 'p')].edge_index = pos

    for r in ratio:
        mask = train_test_split(
            g.nodes['p'].data['label'].detach().cpu().numpy(), seed=np.random.randint(0, 35456, size=1),
            train_examples_per_class=r,
            val_size=1000, test_size=None)
        train_mask_l = f"{r}_train_mask"
        train_mask = mask['train'].astype(bool)
        val_mask_l = f"{r}_val_mask"
        val_mask = mask['val'].astype(bool)

        test_mask_l = f"{r}_test_mask"
        test_mask = mask['test'].astype(bool)

        g.nodes['p'].data[train_mask_l] = torch.from_numpy(train_mask)
        g.nodes['p'].data[val_mask_l] = torch.from_numpy(val_mask)
        g.nodes['p'].data[test_mask_l] = torch.from_numpy(test_mask)

    return g

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--model', '-m', default='RGCN', type=str, help='name of models')
    parser.add_argument('--dataset', '-d', default='acm', type=str, help='acm or cora')
    parser.add_argument('--gpu', '-g', default='-1', type=int, help='-1 means cpu')
    parser.add_argument('--mini-batch-flag', action='store_true')

    args = parser.parse_args()

    ds = MyNCDataset()
    new_ds = AsNodeClassificationDataset(ds, target_ntype='author', labeled_nodes_split_ratio=[0.8, 0.1, 0.1],
                                         prediction_ratio=1, label_mask_feat_name='label_mask')

    experiment = Experiment(conf_path='./my_config.ini', max_epoch=1, model=args.model, dataset=new_ds,
                            task='node_classification', mini_batch_flag=args.mini_batch_flag, gpu=args.gpu,
                            test_flag=False, prediction_flag=False, batch_size=100, use_uva=False)
    experiment.run()

WARNING:root:The OGB package is out of date. Your version is 1.3.5, while the latest version is 1.3.6.
------------------------------------------------------------------------------
 Basic setup of this experiment: 
     model: RGCN    
     dataset: my-nc-dataset-as-nodepred   
     task: node_classification. 
 This experiment has following parameters. You can use set_params to edit them.
 Use print(experiment) to print this information again.
------------------------------------------------------------------------------
batch_size: 100
dataset_name: my-nc-dataset-as-nodepred
device: cpu
dropout: 0.2
fanout: 4
gpu: -1
hidden_dim: 64
hpo_search_space: None
hpo_trials: 100
in_dim: 64
load_from_pretrained: True
lr: 0.01
max_epoch: 0
mini_batch_flag: False
model_name: RGCN
n_bases: 40
num_layers: 3
optimizer: Adam
output_dir: ./openhgnn/output/RGCN
patience: 50
prediction_flag: True
seed: 0
test_flag: False
use_best_config: False
use_self_loop: False
use_uva: False
validation: True
weight_decay: 0.0001

08 May 15:02    INFO  [Config Info] Model: RGCN,    Task: node_classification,  Dataset: Dataset("my-nc-dataset-as-nodepred", num_graphs=1, save_path=/home/yhkj/.dgl/my-nc-dataset-as-nodepred)
08 May 15:02    INFO  [NC Specific] Modify the out_dim with num_classes
Traceback (most recent call last):
  File "/hgnn/inference.py", line 21, in <module>
    prediction_res = experiment.run()
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/experiment.py", line 105, in run
    flow = build_flow(self.config, trainerflow)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/trainerflow/__init__.py", line 46, in build_flow
    return FLOW_REGISTRY[flow_name](args)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/trainerflow/node_classification.py", line 41, in __init__
    self.model = build_model(self.model).build_model_from_args(self.args, self.hg).to(self.device)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/models/RGCN.py", line 41, in build_model_from_args
    return cls(args.hidden_dim,
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/models/RGCN.py", line 73, in __init__
    self.layers.append(RelGraphConvLayer(
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/openhgnn/models/RGCN.py", line 167, in __init__
    self.conv = dglnn.HeteroGraphConv({
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/dgl/nn/pytorch/hetero.py", line 132, in __init__
    self.mods = nn.ModuleDict(mods)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/torch/nn/modules/container.py", line 322, in __init__
    self.update(modules)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/torch/nn/modules/container.py", line 398, in update
    self[key] = module
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/torch/nn/modules/container.py", line 329, in __setitem__
    self.add_module(key, module)
  File "/home/yhkj/anaconda3/envs/ssl/lib/python3.8/site-packages/torch/nn/modules/module.py", line 388, in add_module
    raise KeyError("attribute '{}' already exists".format(name))
KeyError: "attribute 'to' already exists"

Process finished with exit code 1

Hello, dear author! I followed the official example strictly, but returned an error on my own dataset! I would like to know this is the reason. Thank you for your help.

BUPT-GAMMA / OpenHGNN

Run Example #169

❓ Questions and Help