pytorch中的forward函数详细理解

看了好多博客，没有把forward讲明白。其实非常简单！

class Student(object):
    def __init__(self, name):
        self.name = name

    def __call__(self):
        print('My name is %s.' % self.name) 
        self.forward()
    def forward(self):
        print('Student')
class herry(Student):
    def __init__(self, name):
        self.name = name
    def forward(self):
        print('herry')

student = herry('bob')
student()

打印结果如下：

My name is bob.
herry

深度学习网络框架中每次都有super，那它的作用是干什么？

class Student(object):
    def __init__(self, name):
        print('2')
        self.name = name

    def __call__(self):
        print('My name is %s.' % self.name) 
        self.forward()
    def forward(self):
        print('Student')
class herry(Student):
    def __init__(self, name):
        print('1')
        super(herry,self).__init__(name)#若不写这句话，进入不到父类的初始函数中去
        self.name = name
    def forward(self):
        print('herry')

student = herry('bob')
student()

打印结果

1
2
My name is bob.
herry

 可以看出是为了父类函数的初始化。