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'

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
Logo

有“AI”的1024 = 2048,欢迎大家加入2048 AI社区

更多推荐