ValueError and RuntimeError

[sgybupt]

Hi, have you ever met this Error?

• when i valuate my model, with shape(1, 3, 256, 256) imgTensor input, this Error raised up:

Traceback (most recent call last):
  File "/home/elaine/su/track2/Person-reID-triplet-loss-master/my_test.py", line 432, in <module>
    print(model(imgtrans))
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/elaine/su/track2/Person-reID-triplet-loss-master/model.py", line 86, in forward
    x, f = self.classifier(x)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/elaine/su/track2/Person-reID-triplet-loss-master/model.py", line 54, in forward
    f = self.add_block(x)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/container.py", line 91, in forward
    input = module(input)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 45, in forward
    self._check_input_dim(input)
  File "/home/elaine/anaconda3/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 123, in _check_input_dim
    .format(input.dim()))
ValueError: expected 2D or 3D input (got 1D input)

I'm sure that the input tenor shape is (1, 3, 256, 256)
And i have changed mode of models into mode:eval()

print('-------test-----------')
model_structure = ft_net(opt.nclasses)
model = load_network(model_structure)
model = model.eval()  # Change to test mode
model.train(False)

if use_gpu:
    model = model.cuda()

with torch.no_grad():
    # predicts = extract_feature_cls(model, dataloaders['val'], mode='cls')
    # predicts = np.argmax(predicts, axis=0)
    temimg = Image.open('/home/elaine/su/track2/Market/pytorch/image_query/000001.jpg')
    imgtrans = data_transforms(temimg)
    imgtrans = imgtrans.unsqueeze(0)
    print(imgtrans.shape) # torch.Size([1, 3, 256, 256])
    imgtrans = Variable(imgtrans.cuda())
    print(model(imgtrans))

[sgybupt]

Thanks a lot for your work. i have got this.
input.shape must be at least (Batch, 3, 256, 256) Batch larger than 2