Pytorch 几何：RuntimeError：预期的标量类型 Long 但发现 Float

Question

I have gone through all the similar threads and even sought help via github.

import torch
from scipy.sparse import coo_matrix
from torch_geometric.data import Data, Dataset, download_url
import numpy as np
from sklearn.preprocessing import MinMaxScaler
import pandas as pd

def graph_data(A, X, labels):

    tg_graphs = []
    sc = MinMaxScaler()

    y_train = np.array(labels)
    y_train = sc.fit_transform(y_train.reshape((-1,1)))
    y_train = torch.from_numpy(y_train).view(-1,1)

    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, dtype=torch.long)

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

        tg_graphs.append(graph)

    return tg_graphs, y_train

The code above is how i create the dataset.

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[:33000]
test_dataset = dataset[33000:]

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, 1)

    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=3)
print(model)
#%%
model = GCN(hidden_channels=64)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
criterion = torch.nn.functional.mse_loss

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.reshape(-1,1), 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 this is my model code.

RuntimeError                              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()
      6 model.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.

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 [5], 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:191, in GCNConv.forward(self, x, edge_index, edge_weight)
    188         else:
    189             edge_index = cache
--> 191 x = self.lin(x)
    193 # propagate_type: (x: Tensor, edge_weight: OptTensor)
    194 out = self.propagate(edge_index, x=x, edge_weight=edge_weight,
    195                      size=None)

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\dense\linear.py:118, in Linear.forward(self, x)
    113 def forward(self, x: Tensor) -> Tensor:
    114     r"""
    115     Args:
    116         x (Tensor): The features.
    117     """
--> 118     return F.linear(x, self.weight, self.bias)
RuntimeError: expected scalar type Long but found Float

And that is the error. I have tried so many different ways to convert the tensor to Long.

The targets is this:

0         0.091205
1         0.091156
2         0.093943
3         0.091148
4         0.091168
           ...    
43244    20.438217
43245    20.438217
43246    20.438217
43247    20.438217
43248    20.438217

My goal is linear regression, where the above is y and x are the corresponding graphs.

Answer 1

The reason lays in:

The input x's dtype is "torch.int64", after GCNConv the x changes to "torch.float32",but it also expects torch.int64"

Solve way

x=x.type(torch.float)