喀拉拉邦一维阵列的置换特征

问题描述 投票:0回答:1

我想在交换要素到另一层之前交换它们。我有4个变量,所以我的输入数组的大小为(#samples,4)

让我们说这些特征是:x1,x2,x3,x4

例外的输出:

交换1:x4,x3,x2,x1

交换2:x2,x3,x2,x1

…。等

这是我尝试过的

def toy_model():    
   _input = Input(shape=(4,))
   perm = Permute((4,3,2,1)) (_input)
   dense = Dense(1024)(perm)
   output = Dense(1)(dense)

   model = Model(inputs=_input, outputs=output)
   return model

   toy_model().summary()
   ValueError: Input 0 is incompatible with layer permute_58: expected ndim=5, found ndim=2

但是,Permute层期望多维数组对数组进行置换,因此它无法完成工作。反正喀拉拉邦有什么可以解决的吗?

我也试图将流动函数作为Lambda层提供,但出现错误

def permutation(x):
   x = keras.backend.eval(x)
   permutation = [3,2,1,0]
   idx = np.empty_like(x)
   idx[permutation] = np.arange(len(x))
   permutated = x[:,idx]
   return K.constant(permutated)

ValueError: Layer dense_93 was called with an input that isn't a symbolic tensor. Received type:                                                
<class 'keras.layers.core.Lambda'>. Full input: [<keras.layers.core.Lambda object at 
0x7f20a405f710>]. All inputs to the layer should be tensors.
keras swap layer tf.keras permute
1个回答
0
投票

[将Lambda层与某些后端功能一起使用或与slices + concat一起使用。

4,3,2,1

perm = Lambda(lambda x: tf.reverse(x, axis=-1))(_input)

2,3,2,1

def perm_2321(x):
    x1 = x[:, 0]
    x2 = x[:, 1]
    x3 = x[:, 2]

    return tf.stack([x2,x3,x2,x1], axis=-1)

perm = Lambda(perm_2321)(_input)
© www.soinside.com 2019 - 2024. All rights reserved.