问题：RT，下一组数据集的又变成RuntimeError: The size of tensor a (30) must match the size of tensor b (36) at non-singleton dimension 0，后面tensor b的值在不断变化
解决：全景分割里面初始设定的mask的数量是30个，数据集里的mask多于了30个，这时需要把初始mask数量调大
后续问题：初始设定的mask过大，会导致显存占用过大，因为它会让所有数据集的mask数扩大为设定的数量
免责声明！
本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。
猜您在找
the size of tensor a (539) must match the size of tensor b (512) at non-singleton dimension 1
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1 #805
RuntimeError:stack expects each tensor to be equal size,but got [3,224,244] at entry 0 and [1,224,244] at entry 7
RuntimeError: cuda runtime error (30) : unknown errorr
RuntimeError: zero-dimensional tensor (at position 0) cannot be concatenated
RuntimeError: one_hot is only applicable to index tensor
the-trustanchors-parameter-must-be-non-empty
has invalid type , must be a string or Tensor
张量与数组运算报错(Use Tensor.cpu() to copy the tensor to host memory first;RuntimeError: Expected all tensors to be on the same device)
#报错记录#RuntimeError: Expected tensor for 'out' to have the same device as tensor for argument #2 'mat1'; but device 1 does not equal 0 (while checking arguments for addmm)