Pytorch常见问题

1. Jacobian mismatch for output 0 with respect to input 0,
   numerical
   

   链接１

2. AttributeError: cannot assign module before Module.__init__() call
   

   调用了自定义的类，但是 在自定义的类的__init__函数下面没有写super( XXX, self ).init()

   class XXX( nn.Module ):
   def init(self, 等等):

   ​ super( XXX, self ).init()

3. RuntimeError: output with shape [1, 224, 224] doesn't match the broadcast shape [3, 224, 224]
   

   链接

4. Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

   链接

5. h5py_init_.py:26：FutureWarning: Conversion of the second argument of issubdtype from float tosadf

   链接

6. No module named ‘_main_.model’； ‘_main_’ is not a package

   问题描述：未指定当前目录根目录

   链接

   不定期更新中．．．．．．