ValueError: Expected input batch_size (1) to match target batch_size (0).

[anthonysirico]

Here is the dataset creation code, following this I ran torch.save('dataset.pt').

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 = []
    labels = torch.FloatTensor(labels)

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

        tg_graphs.append(graph)

    return tg_graphs

After that, I ran my model:

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)
#%%
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.reshape(-1,1), 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}')

And received the following error:

ValueError                                Traceback (most recent call last)
Input In [7], 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 [6], in train()
      8 for data in train_loader.dataset:  # Iterate in batches over the training dataset.
      9     out = model(data.x.reshape(-1,1), data.edge_index, data.batch)  # Perform a single forward pass.
---> 10     loss = criterion(out, data.y)  # Compute the loss.
     11     loss.backward()  # Derive gradients.
     12     optimizer.step()  # Update parameters based on 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 = [], []

File ~\anaconda3\lib\site-packages\torch\nn\modules\loss.py:1163, in CrossEntropyLoss.forward(self, input, target)
   1162 def forward(self, input: Tensor, target: Tensor) -> Tensor:
-> 1163     return F.cross_entropy(input, target, weight=self.weight,
   1164                            ignore_index=self.ignore_index, reduction=self.reduction,
   1165                            label_smoothing=self.label_smoothing)
File ~\anaconda3\lib\site-packages\torch\nn\functional.py:2996, in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
   2994 if size_average is not None or reduce is not None:
   2995     reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2996 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)

ValueError: Expected input batch_size (1) to match target batch_size (0).

Does it have to do with the cross entropy or the way my dataset is created?

[rusty1s]

What are the shapes of out and data.y before

loss = criterion(out, data.y)  # Compute the loss.

[rusty1s]

I think your implementation looks good to me, and I think using the homogeneous data object works just fine in your case.. Probably worth to use an InMemoryDataset rather than a Dataset it it fits into memory. This also allows you to use dataset.data.

[anthonysirico]

Ok, gotcha. I read the article from the stanford folks https://medium.com/stanford-cs224w/using-gnns-and-protein-expression-networks-to-predict-alzheimers-disease-diagnosis-72c229efeb49 and they mention that while using Networkx, they used nx.set_node_attributes to bring in the string labels. Then after using torch_geometric.utils.from_networkx it brings it over as another attribute. So if i set node attributes to my node labels and keep them as strings, how can my model train on that?

[rusty1s]

You still need to convert your strings to a numerical representation. The mapping_dict approach mentioned early is exactly what achieves this.

[anthonysirico]

Thanks to your help, i did it! I have a working model that's getting 83% accuracy. Now, how can i analyze the results? How do you make predictions with this? It doesn't seem as simple as TensorFlow using model.predict(). This is how i ran the model:

class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(GCN, self).__init__()
        torch.manual_seed(12345)
        self.conv1 = GraphConv(dataset.num_node_features, hidden_channels)
        self.conv2 = GraphConv(hidden_channels, hidden_channels)
        self.conv3 = GraphConv(hidden_channels, hidden_channels)
        self.lin = Linear(hidden_channels, dataset.num_classes)

    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)

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:  # 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}')

and one graph is Data(edge_index=[2, 32], component=[14], weight=[32], num_nodes=14, x=[14, 3], y=[1])

[rusty1s]

Making predictions is similar to any other PyTorch model. IMO, you should be able to simply load in your pre-trained model, and run it:

model = torch.load(...)
model.eval()

# load inference data
data = ...

pred = model(data.x, data.edge_index, batch=edge_index.new_zeros(data.x.size(0)))