用PyTorch跑旧模型代码时候报错:
RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method. (Example: https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function)
意识是autograd在新版中不能用非静态方法,要用动态方法,出错的地方是前向传播处:
def forward(self, image):
解决方法,在forward上面加上 @staticmethod
:
@staticmethod
def forward(self, image):
运行后,又报错:
TypeError: forward() missing 1 required positional argument: 'image'
查PyTorch文档,发现解决方法:
当forward变成静态方法后,调用时可使用.apply():
net = Model()
y = net.apply(x) #原来是y = net(x)调用前向传播函数,但是这里改用.apply()调用