想要深入了解《Pyramid Stereo Matching Network》这篇论文，还是需要去看代码。下面就debug，代码，看方法执行的一个过程。

我选择的是submissuib.py文件。在
pred_disp=test(imgL,imgR)
这一行设置断点。开始debug。执行step into。
首先进入到module.py文件的 eval()方法中。

     def eval(self):
        Sets the module in evaluation mode.

        This has any effect only on certain modules. See documentations of
        particular modules for details of their behaviors in training/evaluation
        mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
        etc.
    
        return self.train(False)

接着eval()方法会调用 train()方法。开始训练。进入train()方法：

    def train(self, mode=True):
        r"""Sets the module in training mode.

        This has any effect only on certain modules. See documentations of
        particular modules for details of their behaviors in training/evaluation
        mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
        etc.

        Returns:
            Module: self
        """
        self.training = mode
        for module in self.children():
            module.train(mode)
        return self

开始会执行 self.training=mode这一行代码， 然后调用自身的 __setattr__方法，