RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously

Traceback (most recent call last):
  File "E:/Program Files/PyCharm 2019.2/PyG/test.py", line 70, in 
    loss.backward()  # 反向传播计算梯度
  File "F:Anaconda3libsite-packagestorch_tensor.py", line 307, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
  File "F:Anaconda3libsite-packagestorchautograd__init__.py", line 156, in backward
    allow_unreachable=True, accumulate_grad=True)  # allow_unreachable flag
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

搭建GCN模型时：

self.conv1 = GCNConv(features, 32)
self.conv2 = GCNConv(32, classes)

classes与原始数据的类别数不一致。

self.conv2 = GCNConv(32, dataset.num_classes)