2.3节关于grad_fn的测试代码在PyTorch 1.3.1中运行结果与说明不符

[lon91ong]

bug描述 grad_fn的测试代码在PyTorch 1.3.1中运行结果与说明不符

y = x + 2
...
print(y.grad_fn) #output None

2.3.3小节第一段代码运行报错

out.backward() # 等价于 out.backward(torch.tensor(1.))
print(x.grad)

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-23-5b0e34440c47> in <module>
----> 1 out.backward() # 等价于 out.backward(torch.tensor(1.))
      2 print(x.grad)

/mnt/e/Programs/SageMath/local/lib/python3.7/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
    164                 products. Defaults to ``False``.
    165         """
--> 166         torch.autograd.backward(self, gradient, retain_graph, create_graph)
    167 
    168     def register_hook(self, hook):

/mnt/e/Programs/SageMath/local/lib/python3.7/site-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
     97     Variable._execution_engine.run_backward(
     98         tensors, grad_tensors, retain_graph, create_graph,
---> 99         allow_unreachable=True)  # allow_unreachable flag
    100 
    101 

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

版本信息 pytorch:1.3.1+cpu ...

[lon91ong]

重启kernel之后, 莫名其妙的不报错了!