小编Jak*_*lan的帖子

我正在尝试使用本教程加载模型：https : //pytorch.org/tutorials/beginner/saving_loading_models.html#saving-loading-model-for-inference。不幸的是，我非常初学者，我面临一些问题。

我创建了检查点：

checkpoint = {'epoch': epochs, 'model_state_dict': model.state_dict(), 'optimizer_state_dict': optimizer.state_dict(),'loss': loss}
torch.save(checkpoint, 'checkpoint.pth')

然后我为我的网络编写了类，我想加载文件：

class Network(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(9216, 4096)
        self.fc2 = nn.Linear(4096, 1000)
        self.fc3 = nn.Linear(1000, 102)

    def forward(self, x):
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        x = F.relu(x)
        x = self.fc3(x)
        x = log(F.softmax(x, dim=1))
        return x

像那样：

def load_checkpoint(filepath):
    checkpoint = torch.load(filepath)
    model = Network()
    model.load_state_dict(checkpoint['model_state_dict'])
    optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
    epoch = checkpoint['epoch']
    loss = checkpoint['loss']

model = load_checkpoint('checkpoint.pth')

我收到此错误（已编辑以显示整个通信）： …

这是我的代码:

dictionary = {}
for i in range(2, 15):
    dictionary[str(i)] = 0

是否可以用一行代码创建它？