ValueError: Expected more than 1 spatial element when training, got input size torch.Size([1, 32, 1])

[cuiyun-fang]

@HeatherJiaZG 您好！感谢您提供的代码！但是我在运行python train.py时出现了以下报错：
Traceback (most recent call last): File "/home/jhk/work code/SuperGlue-pytorch-master/train.py", line 172, in <module> data = superglue(pred) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/jhk/work code/SuperGlue-pytorch-master/models/superglue.py", line 262, in forward desc1 = desc1 + self.kenc(kpts1, torch.transpose(data['scores1'], 0, 1)) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/jhk/work code/SuperGlue-pytorch-master/models/superglue.py", line 83, in forward return self.encoder(torch.cat(inputs, dim=1)) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/container.py", line 139, in forward input = module(input) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/instancenorm.py", line 72, in forward return self._apply_instance_norm(input) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/modules/instancenorm.py", line 32, in _apply_instance_norm return F.instance_norm( File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/functional.py", line 2482, in instance_norm _verify_spatial_size(input.size()) File "/home/jhk/anaconda3/envs/openglue/lib/python3.8/site-packages/torch/nn/functional.py", line 2449, in _verify_spatial_size raise ValueError("Expected more than 1 spatial element when training, got input size {}".format(size)) ValueError: Expected more than 1 spatial element when training, got input size torch.Size([1, 32, 1])
请问您事先对数据集是否进行过其他处理，或者您是否知道这个报错如何能解决？万分感谢！

[lihaoling]

I also encountered the same problem, please tell me if you solved it

[xiao-longlong]

我也遇到了类似的问题，如下
File "/workspace/train.py", line 172, in
data = superglue(pred)
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/workspace/models/superglue.py", line 260, in forward
desc1 = desc1 + self.kenc(kpts1, torch.transpose(data['scores1'], 0, 1))
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/workspace/models/superglue.py", line 83, in forward
return self.encoder(torch.cat(inputs, dim=1))
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/container.py", line 204, in forward
input = module(input)
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/instancenorm.py", line 74, in forward
return self._apply_instance_norm(input)
File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/instancenorm.py", line 34, in _apply_instance_norm
return F.instance_norm(
File "/usr/local/lib/python3.9/dist-packages/torch/nn/functional.py", line 2494, in instance_norm
_verify_spatial_size(input.size())
File "/usr/local/lib/python3.9/dist-packages/torch/nn/functional.py", line 2461, in _verify_spatial_size
raise ValueError("Expected more than 1 spatial element when training, got input size {}".format(size))
ValueError: Expected more than 1 spatial element when training, got input size torch.Size([1, 32, 1])
而且此问题发生在第一个epoch的中间，并不是一开始就出现维度错误。

[pureloveljc]

load_data

if len(kp1) <= 1 or len(kp2) <= 1:

[ttaohe]

encoder

请问这个是添加到哪里呢？

[Syfback]

raceback (most recent call last):
File "Y:\torch_xiangmu\SuperGlue-pytorch-master\train.py", line 172, in
data = superglue(pred)
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\torch_xiangmu\SuperGlue-pytorch-master\models\superglue.py", line 257, in forward
desc1 = desc1 + self.kenc(kpts1, torch.transpose(data['scores1'], 0, 1))
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\torch_xiangmu\SuperGlue-pytorch-master\models\superglue.py", line 83, in forward
return self.encoder(torch.cat(inputs, dim=1))
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
input = module(input)
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\instancenorm.py", line 74, in forward
return self._apply_instance_norm(input)
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\modules\instancenorm.py", line 34, in _apply_instance_norm
return F.instance_norm(
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\functional.py", line 2494, in instance_norm
_verify_spatial_size(input.size())
File "Y:\Anaconda3\envs\syf\lib\site-packages\torch\nn\functional.py", line 2461, in _verify_spatial_size
raise ValueError("Expected more than 1 spatial element when training, got input size {}".format(size))
ValueError: Expected more than 1 spatial element when training, got input size torch.Size([1, 32, 1])
我也有这样的问题，请问怎么解决呢？