import torchfrom torch.autograd import Variabletensor = torch.FloatTensor([[1, 2], [3, 4]])variable = Variable(tensor, requires_grad=True)print(tensor)    # tensor([[1., 2.], [3., 4.]])print(variable)  # tensor([[1., 2.], [3., 4.]], requires_grad=True) 梯度设置为True,反向传播要使用t_out = torch.mean(tensor*tensor)  # x^2v_out = torch.mean(variable*variable)print(t_out)      # tensor(7.5000)   变量计算的时候比张量多了一个梯度信息print(v_out)      # tensor(7.5000, grad_fn=
    
     )v_out.backward()  # 反向传播# v_out = 1/4*sun(var*var)                       # 求导过程# d(v_out)/d(var) = 1/4*2*variable = variable/2  # 求导过程print(variable.grad)  # tensor([[0.5000, 1.0000], [1.5000, 2.0000]])print("variable:", variable)                          # tensor([[1., 2.], [3., 4.]], requires_grad=True)print("variable.data:", variable.data)                # tensor([[1., 2.], [3., 4.]])print("variable.data.numpy:", variable.data.numpy())  # [[1. 2.] [3. 4.]]
    

END