[英]Concatenate identity matrix to each vector
I want to modify my input by adding several different suffixes to the input vectors.我想通过向输入向量添加几个不同的后缀来修改我的输入。 For example, if the (single) input is [1, 5, 9, 3]
I want to create three vectors (stored as matrix) like this:例如,如果(单个)输入是[1, 5, 9, 3]
我想像这样创建三个向量(存储为矩阵):
[[1, 5, 9, 3, 1, 0, 0],
[1, 5, 9, 3, 0, 1, 0],
[1, 5, 9, 3, 0, 0, 1]]
Of course, this is just one observation so the input to the model is (None, 4)
in this case.当然,这只是一个观察结果,因此在这种情况下(None, 4)
模型的输入是(None, 4)
。 The simple way is to prepare the input data somewhere else (numpy most probably) and adjust the shape of input accordingly.简单的方法是在其他地方准备输入数据(最有可能是numpy)并相应地调整输入的形状。 That I can do but I would prefer doing it inside TensorFlow/Keras.我可以做,但我更喜欢在 TensorFlow/Keras 中做。
I have isolated the problem into this code:我已将此问题隔离到此代码中:
import keras.backend as K
from keras import Input, Model
from keras.layers import Lambda
def build_model(dim_input: int, dim_eye: int):
input = Input((dim_input,))
concat = Lambda(lambda x: concat_eye(x, dim_input, dim_eye))(input)
return Model(inputs=[input], outputs=[concat])
def concat_eye(x, dim_input, dim_eye):
x = K.reshape(x, (-1, 1, dim_input))
x = K.repeat_elements(x, dim_eye, axis=1)
eye = K.expand_dims(K.eye(dim_eye), axis=0)
eye = K.tile(eye, (-1, 1, 1))
out = K.concatenate([x, eye], axis=2)
return out
def main():
import numpy as np
n = 100
dim_input = 20
dim_eye = 3
model = build_model(dim_input, dim_eye)
model.compile(optimizer='sgd', loss='mean_squared_error')
x_train = np.zeros((n, dim_input))
y_train = np.zeros((n, dim_eye, dim_eye + dim_input))
model.fit(x_train, y_train)
if __name__ == '__main__':
main()
The problem seems to be in the -1
in shape
argument in tile
function.问题似乎出在tile
函数中的shape
参数-1
中。 I tried to replace it with 1
and None
.我试图用1
和None
替换它。 Each has its own error:每个都有自己的错误:
-1
: error during model.fit
-1
: model.fit
期间model.fit
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected multiples[0] >= 0, but got -1
1
: error duting model.fit
1
: 误差model.fit
tensorflow.python.framework.errors_impl.InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [32,3,20] vs. shape[1] = [1,3,3]
None
: error during build_model
: None
:在build_model
期间build_model
:
Failed to convert object of type <class 'tuple'> to Tensor. Contents: (None, 1, 1). Consider casting elements to a supported type.
You need to use K.shape()
instead to get the symbolic shape of input tensor.您需要使用K.shape()
来获取输入张量的符号形状。 That's because the batch size is None
and therefore passing K.int_shape(x)[0]
or None
or -1
as a part of the second argument of K.tile()
would not work:这是因为批量大小为None
,因此将K.int_shape(x)[0]
或None
或-1
作为K.tile()
的第二个参数的K.tile()
将不起作用:
eye = K.tile(eye, (K.shape(x)[0], 1, 1))
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.