Traceback (most recent call last):
  File "train_ammeter_twoclass.py", line 189, in <module>
    train(epoch)
  File "train_ammeter_twoclass.py", line 133, in train
    outputs = net(inputs)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/iot/chenjun/1_program/classifer/src/model.py", line 79, in forward
    x = self.net(x)             # inception will return two matrices
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torchvision/models/inception.py", line 109, in forward
    aux = self.AuxLogits(x)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torchvision/models/inception.py", line 308, in forward
    x = self.conv1(x)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torchvision/models/inception.py", line 326, in forward
    x = self.bn(x)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 66, in forward
    exponential_average_factor, self.eps)
  File "/home/iot/miniconda2/envs/pytorch3/lib/python3.6/site-packages/torch/nn/functional.py", line 1251, in batch_norm
    raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size [1, 768, 1, 1]

Problem analysis: batch nomolization is used in the model. When batch is used in training, there should be an odd number. For example, the total number of samples of dataset is 17, and your batch number is 0_ If the size is 8, such an error will be reported.
Solution: delete a sample from the dataset.

Converted from: valueerror: expected more than 1 value per channel when training, got input size torch.Size ([1, 768, 1, 1])