Dimension out of range

[anthonysirico]

import torch
import numpy as np
from scipy.sparse import coo_matrix
from torch_geometric.data import Data, Dataset, download_url

def graph_data(A, X, labels):

    tg_graphs = []

    for i in range(len(A)):
        coo = coo_matrix(A[i])
        indices = np.vstack((coo.row, coo.col))
        x = [ord(i) for i in X[i]]
        index = torch.LongTensor(indices)
        feature = torch.FloatTensor(x)

        graph = Data(x=feature, edge_index=index, y=labels[i])

        tg_graphs.append(graph)

    return tg_graphs


import torch

dataset = torch.load('data/dataset.pt')

data = dataset[0]  # Get the first graph object.

print()
print(data)
print('=============================================================')

# Gather some statistics about the first graph.
print(f'Number of nodes: {data.num_nodes}')
print(f'Number of edges: {data.num_edges}')
print(f'Average node degree: {data.num_edges / data.num_nodes:.2f}')
print(f'Has isolated nodes: {data.has_isolated_nodes()}')
print(f'Has self-loops: {data.has_self_loops()}')
print(f'Is undirected: {data.is_undirected()}')

train_dataset = dataset[:5000]
test_dataset = dataset[5000:]

print(f'Number of training graphs: {len(train_dataset)}')
print(f'Number of test graphs: {len(test_dataset)}')

from torch_geometric.loader import DataLoader

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

for step, data in enumerate(train_loader):
    print(f'Step {step + 1}:')
    print('=======')
    print(f'Number of graphs in the current batch: {data.num_graphs}')
    print(data)
    print()

from torch.nn import Linear
import torch.nn.functional as F
from torch_geometric.nn import GCNConv
from torch_geometric.nn import global_mean_pool

class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(GCN, self).__init__()
        torch.manual_seed(12345)
        self.conv1 = GCNConv(-1, hidden_channels)
        self.conv2 = GCNConv(hidden_channels, hidden_channels)
        self.conv3 = GCNConv(hidden_channels, hidden_channels)
        self.lin = Linear(hidden_channels, 35609)

    def forward(self, x, edge_index, batch):
        # 1. Obtain node embeddings
        x = self.conv1(x, edge_index)
        x = x.relu()
        x = self.conv2(x, edge_index)
        x = x.relu()
        x = self.conv3(x, edge_index)

        # 2. Readout layer
        x = global_mean_pool(x, batch)  # [batch_size, hidden_channels]

        # 3. Apply a final classifier
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.lin(x)

        return x

model = GCN(hidden_channels=64)
print(model)

from IPython.display import Javascript
display(Javascript('''google.colab.output.setIframeHeight(0, true, {maxHeight: 300})'''))

model = GCN(hidden_channels=64)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
criterion = torch.nn.CrossEntropyLoss()

def train():
    model.train()

    for data in train_loader.dataset:  # Iterate in batches over the training dataset.
        out = model(data.x, data.edge_index, data.batch)  # Perform a single forward pass.
        loss = criterion(out, data.y)  # Compute the loss.
        loss.backward()  # Derive gradients.
        optimizer.step()  # Update parameters based on gradients.
        optimizer.zero_grad()  # Clear gradients.

def test(loader):
    model.eval()

    correct = 0
    for data in loader:  # Iterate in batches over the training/test dataset.
        out = model(data.x, data.edge_index, data.batch)
        pred = out.argmax(dim=1)  # Use the class with highest probability.
        correct += int((pred == data.y).sum())  # Check against ground-truth labels.
    return correct / len(loader.dataset)  # Derive ratio of correct predictions.

for epoch in range(1, 171):
    train()
    train_acc = test(train_loader)
    test_acc = test(test_loader)
    print(f'Epoch: {epoch:03d}, Train Acc: {train_acc:.4f}, Test Acc: {test_acc:.4f}')

Above is the code, I have 43,000 plut graphs in a list that look like this:

[Data(x=[18], edge_index=[2, 42], y=0.0912047881539918),
 Data(x=[18], edge_index=[2, 42], y=0.0911561592893587),
 Data(x=[17], edge_index=[2, 40], y=0.0939426626061364),
 Data(x=[17], edge_index=[2, 40], y=0.0911476283054859),
 Data(x=[18], edge_index=[2, 42], y=0.0911682263035731),
 Data(x=[19], edge_index=[2, 40], y=0.0885647857159851),
 Data(x=[19], edge_index=[2, 40], y=0.0901584221915995),
 Data(x=[19], edge_index=[2, 40], y=0.0901584221916017),
 Data(x=[19], edge_index=[2, 40], y=0.0716963824344366),
 Data(x=[20], edge_index=[2, 42], y=0.0786077013779856),
 Data(x=[19], edge_index=[2, 40], y=0.0946293611737009),
 Data(x=[20], edge_index=[2, 42], y=0.0691385630931132),
 Data(x=[18], edge_index=[2, 38], y=0.0939426621168369),
 Data(x=[19], edge_index=[2, 40], y=0.0805215970455449),
...

But, when i run the data through the model, I get:

IndexError                                Traceback (most recent call last)
Input In [9], in <cell line: 1>()
      1 for epoch in range(1, 171):
----> 2     train()
      3     train_acc = test(train_loader)
      4     test_acc = test(test_loader)

Input In [8], in train()
      6 model.train()
      8 for data in train_loader.dataset:  # Iterate in batches over the training dataset.
----> 9     out = model(data.x, data.edge_index, data.batch)  # Perform a single forward pass.
     10     loss = criterion(out, data.y)  # Compute the loss.
     11     loss.backward()  # Derive gradients.

File ~\anaconda3\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
   1106 # If we don't have any hooks, we want to skip the rest of the logic in
   1107 # this function, and just call forward.
   1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1109         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110     return forward_call(*input, **kwargs)
   1111 # Do not call functions when jit is used
   1112 full_backward_hooks, non_full_backward_hooks = [], []

Input In [6], in GCN.forward(self, x, edge_index, batch)
     15 def forward(self, x, edge_index, batch):
     16     # 1. Obtain node embeddings
---> 17     x = self.conv1(x, edge_index)
     18     x = x.relu()
     19     x = self.conv2(x, edge_index)

File ~\anaconda3\lib\site-packages\torch\nn\modules\module.py:1110, in Module._call_impl(self, *input, **kwargs)
   1106 # If we don't have any hooks, we want to skip the rest of the logic in
   1107 # this function, and just call forward.
   1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1109         or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110     return forward_call(*input, **kwargs)
   1111 # Do not call functions when jit is used
   1112 full_backward_hooks, non_full_backward_hooks = [], []

File ~\anaconda3\lib\site-packages\torch_geometric\nn\conv\gcn_conv.py:173, in GCNConv.forward(self, x, edge_index, edge_weight)
    170 cache = self._cached_edge_index
    171 if cache is None:
    172     edge_index, edge_weight = gcn_norm(  # yapf: disable
--> 173         edge_index, edge_weight, x.size(self.node_dim),
    174         self.improved, self.add_self_loops)
    175     if self.cached:
    176         self._cached_edge_index = (edge_index, edge_weight)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got -2)

Help me please!

[AmEskandari]

Hi
I think if you change the nodes feature shape to (number of nodes, node feature dimension) your problem will be solved. I guess your input dimension is one so you can use the below code instead of what you used.

out = model(data.x.reshape(-1,1), data.edge_index, data.batch)

[anthonysirico]

Worked, thanks so much.