懷疑是因為安裝了和cuda不匹配的torch 導致的，本地的ubuntu是cuda 11.0,安裝了cuda 11.3.
只能刪除虛擬環境，重新安裝，根據提示逐步安裝 pip install torch
免責聲明！
本站轉載的文章為個人學習借鑒使用，本站對版權不負任何法律責任。如果侵犯了您的隱私權益，請聯系本站郵箱yoyou2525@163.com刪除。
猜您在找
import pandas出現‘ValueError: numpy.ufunc size changed, may indicate binary incompatibility. Expected 216 from C header, got 192 from PyObject’問題
安裝Python3.6.4后，在使用numpy時報錯RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
numpy.ufunc size changed, may indicate binary incompatibility錯誤解決
Python：Expected 88 from C header, got 80 from PyObjec
解決Tensorflow ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray)
pytorch報錯：ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1,512,1,1])
將numpy.ndarray寫入excel
numpy.ndarray的賦值操作
TypeError: unhashable type: 'numpy.ndarray'
ValueError:Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])