Pytorch 如何避免正确创建网络结构
我试图在我的神经网络模型中定义feedforwad函数:Pytorch 如何避免正确创建网络结构,pytorch,Pytorch,我试图在我的神经网络模型中定义feedforwad函数: class FeedForward(nn.Module): def __init__(self): super(FeedForward,self).__init__() self.fc1 = nn.Linear(784, 256) self.fc2 = nn.Linear(256, 64) self.fc2 = nn.Linear(64, 10) def
class FeedForward(nn.Module):
def __init__(self):
super(FeedForward,self).__init__()
self.fc1 = nn.Linear(784, 256)
self.fc2 = nn.Linear(256, 64)
self.fc2 = nn.Linear(64, 10)
def feedforward(self, x):
x = x.view(x.shape[0], -1) # make sure inputs are flattened
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.relu(self.fc3(x))
x= F.log_softmax(x, dim=1) # preserve batch dim
return x
消息说:
未实现错误
我不确定我遗漏了什么。方法名称必须是
forward
,而不是feedforward
:
类前馈(nn.模块):
定义初始化(自):
超级(前馈,自)。\uuuu初始化
self.fc1=nn.Linear(784256)
self.fc2=nn.Linear(256,64)
self.fc2=nn.Linear(64,10)
def前锋(赛尔夫,x):#这正是皮托克所期望的
x=x.view(x.shape[0],-1)#确保输入是平坦的
x=F.relu(自fc1(x))
x=F.relu(自身fc2(x))
x=F.relu(自身fc3(x))
x=F.log_softmax(x,dim=1)#保留批量dim
返回x