ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

Traceback (most recent call last):
  File "train.py", line 82, in <module>
    main(config)
  File "train.py", line 60, in main
    trainer.train()
  File "/opt/ml/segmentation/semantic-segmentation-level2-cv-02/base/base_trainer.py", line 63, in train
    result = self._train_epoch(epoch)
  File "/opt/ml/segmentation/semantic-segmentation-level2-cv-02/trainer/trainer.py", line 56, in _train_epoch
    output = self.model(data)['out']
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/ml/segmentation/semantic-segmentation-level2-cv-02/model/basic_model.py", line 37, in forward
    return self.model(x)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torchvision/models/segmentation/_utils.py", line 24, in forward
    x = self.classifier(x)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torchvision/models/segmentation/deeplabv3.py", line 91, in forward
    res.append(conv(x))
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torchvision/models/segmentation/deeplabv3.py", line 61, in forward
    x = mod(x)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 136, in forward
    self.weight, self.bias, bn_training, exponential_average_factor, self.eps)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/functional.py", line 2054, in batch_norm
    _verify_batch_size(input.size())
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/torch/nn/functional.py", line 2037, in _verify_batch_size
    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 torch.Size([1, 256, 1, 1])
Exception ignored in: <function tqdm.__del__ at 0x7f4f5f354320>
Traceback (most recent call last):
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/tqdm/_tqdm.py", line 931, in __del__
    self.close()
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/tqdm/_tqdm.py", line 1133, in close
    self._decr_instances(self)
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/tqdm/_tqdm.py", line 496, in _decr_instances
    cls.monitor.exit()
  File "/opt/conda/envs/segmentation/lib/python3.7/site-packages/tqdm/_monitor.py", line 52, in exit
    self.join()
  File "/opt/conda/envs/segmentation/lib/python3.7/threading.py", line 1041, in join
    raise RuntimeError("cannot join current thread")
RuntimeError: cannot join current thread
config.json에서 모델을 BasicModel2로 변경.
model.eval() 이미 사용 중으로 효과 없음.
drop_last=true 효과 없음.
boostcampaitech2 / semantic-segmentation-level2-cv-02

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1]) #12
