自定义数据集训练报错`The input tensor's dimension should be equal to the axis's size. But received input tensor's dimension is 5, axis's size is 4`

[hhxdestiny]

BML_CodeLab使用UNet3Plus模型训练自定义数据集，in_channels=3，num_classes=2，batch_size=4， 报错如下,

Traceback (most recent call last):
  File "test.py", line 65, in <module>
    use_vdl=True
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddleseg/core/train.py", line 185, in train
    edges=edges)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddleseg/core/train.py", line 46, in loss_computation
    loss_list.append(losses['coef'][i] * loss_i(logits, labels))
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py", line 902, in __call__
    outputs = self.forward(*inputs, **kwargs)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddleseg/models/losses/binary_cross_entropy_loss.py", line 141, in forward
    label = label.transpose((0, 3, 1, 2))
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 5494, in transpose
    out, _ = core.ops.transpose2(x, 'axis', perm)
ValueError: (InvalidArgument) The input tensor's dimension should be equal to the axis's size. But received input tensor's dimension is 5, axis's size is 4
  [Hint: Expected x_rank == axis_size, but received x_rank:5 != axis_size:4.] (at /paddle/paddle/fluid/operators/transpose_op.cc:47)
  [operator < transpose2 > error]

打印了报错行out, _ = core.ops.transpose2(x, 'axis', perm)的参数

x.shape: [1, 512, 512, 3, 2]
perm: (0, 3, 1, 2)

请问可能是哪一块的问题？

[juncaipeng]

paddle中，transpose的输入x和axis必须rank相同。如上，x的rank是5，axis的rank是4，所以报错。

[hhxdestiny]

@juncaipeng 请问输入图片resize后shape: [512, 512, 3]，然后batch_size是1，所以shape应该是[1, 512, 512, 3]，为何打印结果显示x.shape: [1, 512, 512, 3, 2]？第四维的2表示的是label吗？