keras多输出softmax模型输入形状

Question

我有以下模型：

 col1 col2 ... col 4
  1    0         2
  0    0         2
  2    1         1

我的Y具有以下格式：

y = to_categorical(Y).reshape(4, -1, 3)

并通过以下方式重塑：

ValueError: Error when checking model target: the list of Numpy arrays that 
you are passing to your model is not the size the model expected. Expected 
to see 4 array(s), but instead got the following list of 1 arrays: 
[array([[[1., 0., 0.],
    [1., 0., 0.],
    [1., 0., 0.],

但是，在运行fit命令时，出现以下错误：

Array
(
    [0] => Array
        (
            [weight] => 20
        )
    [1] => Array
        (
            [weight] => 15
        )
    [2] => Array
        (
            [weight] => 40
        )
)

Answer 1

假设Y是一个numpy矩阵？ 试试这个：

y = [to_categorical(Y[:, col_numb]).reshape(-1, 3) for col_numb in range(Y.shape[1])]