在 Keras 中创造常量值 [英] Creating constant value in Keras

问题描述

我正在尝试在 keras 模型中创建一个常量变量.到目前为止我所做的是将它作为输入传递.但它始终是一个常量，所以我希望它是一个常量.(每个示例的输入是 [1,2,3...50] => 所以我使用 np.tile(np.array(range(50)),(len(X_input))) 为每个例子重现它)

I am trying to create a constant variable inside a keras model. What I was doing till now is to pass it as Input. But it is always a constant so I want it as a constant.(The input is [1,2,3...50] for each example => so I use np.tile(np.array(range(50)),(len(X_input))) to reproduce it for each example)

所以现在我有:

constant_input = Input(shape=(50,), dtype='int32', name="constant_input")

给出张量:Tensor("constant_input", shape(?,50), dtype=int32)

现在尝试将其作为常量进行:

Now trying to do it as a constant:

np_constant = np.array(list(range(50))).reshape(1, 50)
tf_constant = K.constant(np_constant)
tensor_constant = Input(tensor=tf_constant, shape=(50,), dtype='int32', name="constant_input")

给出一个张量:Tensor("constant_input", shape(50,1),dtype=float32)

但是我要的是每批要缩放的常量，意思就是张量的形状应该是(?, 50)，和Input的使用方式一样.

But What I want is the constant to be scaled in each batch, meaning that the shape of the tensor should be (?, 50), the same as the way of using Input.

能做到吗?

推荐答案

您不能拥有可变大小的常量.常量始终具有相同的值.您可以做的是拥有 (1, 50) 常量，然后在 TensorFlow 中使用 K.tile.也更好地使用 np.arange 而不是 np.array(list(range(50)).类似:

You cannot have a constant with variable size. A constant always has the same value. What you can do is have the (1, 50) constant and then tile it within TensorFlow with K.tile. Also better use np.arange instead of np.array(list(range(50)). Something like:

from keras.layers.core import Lambda
import keras.backend as K

def operateWithConstant(input_batch):
    tf_constant = K.constant(np.arange(50).reshape((1, 50)))
    batch_size = K.shape(input_batch)[0]
    tiled_constant = K.tile(tf_constant, (batch_size, 1))
    # Do some operation with tiled_constant and input_batch
    result = ...
    return result

input_batch = Input(...)
input_operated = Lambda(operateWithConstant)(input_batch)
# continue...

这篇关于在 Keras 中创造常量值的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！