此問題是由於數據類型不匹配導致的，在出錯的數據后面添加.double()
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
RuntimeError: Expected object of backend CUDA but got backend CPU for argument #4 'mat1'
Expected object of backend CPU but got backend CUDA for argument #2 'weight'
Pytorch-loss.backward()-“RuntimeError: Found dtype Double but expected Float”
tensorflow models api:ValueError: Tensor conversion requested dtype string for Tensor with dtype float32: 'Tensor("arg0:0", shape=(), dtype=float32, device=/device:CPU:0)'
RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #4 'mat1'的解決方法
【E-14-Pytorch】RuntimeError: Expected object of device type cuda but got device type cpu for argument #2 'mat1' in call to _th_addmm
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.zeros(shape, dtype=float, order='C')
TypeError: Image data of dtype object cannot be converted to float
keras 報錯 ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("embedding_1/random_uniform:0", shape=(5001, 128), dtype=float32)'