Could not run ‘aten::slow_conv3d_forward‘ with arguments from the ‘CUDA‘ bac

原因: 数据没有给cuda
解决办法

img_patch = torch.tensor(np.expand_dims(img_arr, axis=[0,1])).to(device)

这样就可以啦
Could not run ‘aten::slow_conv3d_forward‘ with arguments from the ‘CUDA‘ bac_第1张图片

你可能感兴趣的:(BUG,python,深度学习,人工智能)