model_classes.py 文件源码

def __init__(self, X, Y, hidden_layer_sizes):
        super(Net, self).__init__()

        # Initialize linear layer with least squares solution
        X_ = np.hstack([X, np.ones((X.shape[0],1))])
        Theta = np.linalg.solve(X_.T.dot(X_), X_.T.dot(Y))

        self.lin = nn.Linear(X.shape[1], Y.shape[1])
        W,b = self.lin.parameters()
        W.data = torch.Tensor(Theta[:-1,:].T)
        b.data = torch.Tensor(Theta[-1,:])

        # Set up non-linear network of 
        # Linear -> BatchNorm -> ReLU -> Dropout layers
        layer_sizes = [X.shape[1]] + hidden_layer_sizes
        layers = reduce(operator.add, 
            [[nn.Linear(a,b), nn.BatchNorm1d(b), nn.ReLU(), nn.Dropout(p=0.2)] 
                for a,b in zip(layer_sizes[0:-1], layer_sizes[1:])])
        layers += [nn.Linear(layer_sizes[-1], Y.shape[1])]
        self.net = nn.Sequential(*layers)
        self.sig = Parameter(torch.ones(1, Y.shape[1]).cuda())