example_tensor.device

example_tensor.shape
example_tensor.size(1)

example_tensor.numel()

example_scalar = example_tensor[1, 1, 0]
example_scalar.item()
example_tensor[:, 0, 0]

torch.ones_like(example_tensor)
torch.zeros_like(example_tensor)
torch.randn_like(example_tensor)
torch.randn(2, 2, device='cpu') # Alternatively, for a GPU tensor, you'd use device='cuda'
torch.arange(4 * 5 * 6).view(4, 5, 6) # shape [4,5,6]

real_clone = real.clone()

F.one_hot(labels % n_classes)

nn.init.xavier_uniform_(tensor) # fill with uniform distribution, values scaled by 'gain'
nn.init.constant_(bias, 0) # fill with constant
nn.init.orthogonal_(param) # with a (semi) orthogonal matrix

(example_tensor - 5) * 2 # 顺序有影响
torch.mul(tensor_x, tensor_x) # 逐元素积
tensor_x * tensor_y # 逐元素积 = torch.mul(x, y)