TensorFlow简单的累积积和产品循环神经网络单元

huangapple go评论60阅读模式
英文:

Tensorflow simple cumulative sum of product RNN cell

问题

我正在尝试构建一个Tensorflow模型,该模型计算两个输入特征的累积乘积之和,即仅在(1,2)上进行预测应该返回2,然后在(2,2)上进行预测应该返回6=(1 * 2) + (2 * 2)

model.predict([1,2])
>>> 2

model.predict([2,2])
>>> 6

model.reset_states()
model.predict([2,2])
>>> 4

我已经尝试过以下方法:

import numpy as np
import tensorflow as tf


class MinimalRNNCell(tf.keras.layers.Layer):

    def __init__(self, units, **kwargs):
        self.states = np.array([0])
        self.state = np.array([0])
        self.units = units
        self.state_size = units
        super(MinimalRNNCell, self).__init__(**kwargs)

    def call(self, inputs, states):
        prev_output = states[0]
        output = tf.math.add(prev_output,inputs)
        
        return output, [output]
    

# Define model
#input
inp = tf.keras.layers.Input(shape=(2,))
#split input
x1,x2 = tf.split(inp, num_or_size_splits=2, axis=1)
#calculate product
product = tf.math.multiply(x1,x2)
#reshape product
time_product = tf.keras.layers.Reshape((1,1))(product)
#Define memory cell and layer
memory_product = MinimalRNNCell(units=1)
layer_product = tf.keras.layers.RNN(memory_product)
#calculate cumulative product
cumulative_product = layer_product(time_product)

output = cumulative_product

model = tf.keras.models.Model(inp, output)


if __name__=="__main__":
    x = np.array([
        [1, 2],
        [2, 2]
    ])

    model.compile()
    y = model.predict(x)
    print()
    print("output: ", y)
>>> [[2],
     [4]]

请注意,我将输入分成两部分的原因是因为这是应该工作的最简单模型。我正在实现的模型更复杂,有更多相互关联的步骤,但我无法让累积部分正常工作。
我觉得类似累积求和的功能可以很容易地使用RNN或LSTM单元实现,但它的工作方式不符合我的预期。

英文:

I am trying to build a Tensorflow model that calculates a cumulative sum of products of two of the input features, i.e. predicting on only (1,2) should return 2, and then predicting on (2,2) should give 6=(1 * 2) + (2 * 2)

model.predict([1,2])
>>> 2

model.predict([2,2])
>>> 6

model.reset_states()
model.predict([2,2])
>>> 4

I have tried the following:

import numpy as np
import tensorflow as tf


class MinimalRNNCell(tf.keras.layers.Layer):

    def __init__(self, units, **kwargs):
        self.states = np.array([0])
        self.state = np.array([0])
        self.units = units
        self.state_size = units
        super(MinimalRNNCell, self).__init__(**kwargs)

    def call(self, inputs, states):
        prev_output = states[0]
        output = tf.math.add(prev_output,inputs)
        
        return output, [output]
    

# Define model
#input
inp = tf.keras.layers.Input(shape=(2,))
#split input
x1,x2 = tf.split(inp, num_or_size_splits=2, axis=1)
#calculate product
product = tf.math.multiply(x1,x2)
#reshape product
time_product = tf.keras.layers.Reshape((1,1))(product)
#Define memory cell and layer
memory_product = MinimalRNNCell(units=1)
layer_product = tf.keras.layers.RNN(memory_product)
#calculate cumulative product
cumulative_product = layer_product(time_product)

output = cumulative_product

model = tf.keras.models.Model(inp, output)


if __name__=="__main__":
    x = np.array([
        [1, 2],
        [2, 2]
    ])

    model.compile()
    y = model.predict(x)
    print()
    print("outptut: ", y)
>>> [[2],
     [4]]

Note the reason i split inputs is because this is the minimal model that should work. The model i am implementing is more complex and has more steps interlinked but it is the accumulation i can't get to work.
I feel like something like a cumulative sum is easily implemented using RNN or LSTM cells, but it does not work how I expect it to.

答案1

得分: 1

如果你只想累积产品,那么请在build()方法中对weight进行初始化,然后每次将model.predict()的结果添加到它上面。以下是代码...

import tensorflow as tf
tf.keras.backend.clear_session()
class CumulativeProduct(tf.keras.layers.Layer):
    def __init__(self):
        super(CumulativeProduct, self).__init__()

    def build(self, input_shape):
        self.cumulative_product = self.add_weight(shape=(), initializer=tf.keras.initializers.Zeros(), trainable=False)

    def call(self, inputs):
        self.cumulative_product.assign(self.cumulative_product + tf.reduce_sum(tf.reduce_prod(inputs, axis=1)))
        return self.cumulative_product
    
    def reset_states(self):
        self.cumulative_product.assign(0.)

inp = tf.keras.layers.Input(shape=(2,))
cumulative_product = CumulativeProduct()
cum_prod = cumulative_product(inp)
model = tf.keras.models.Model(inp, cum_prod)
x = [[1, 2], [2,2]]
model.predict(x)
6.0
x = [[2, 2]]
model.predict(x)
10.0
#重置模型变量
cumulative_product.reset_states()
英文:

If you just want to accumulate the product then initialize the weight on build() method then add each time the result of model.predict() to it. Here is the code...

import tensorflow as tf
tf.keras.backend.clear_session()
class CumulativeProduct(tf.keras.layers.Layer):
    def __init__(self):
        super(CumulativeProduct, self).__init__()

    def build(self, input_shape):
        self.cumulative_product = self.add_weight(shape=(), initializer=tf.keras.initializers.Zeros(), trainable=False)

    def call(self, inputs):
        self.cumulative_product.assign(self.cumulative_product + tf.reduce_sum(tf.reduce_prod(inputs, axis=1)))
        return self.cumulative_product
    
    def reset_states(self):
        self.cumulative_product.assign(0.)

inp = tf.keras.layers.Input(shape=(2,))
cumulative_product = CumulativeProduct()
cum_prod = cumulative_product(inp)
model = tf.keras.models.Model(inp, cum_prod)
x = [[1, 2], [2,2]]
model.predict(x)
6.0
x = [[2, 2]]
model.predict(x)
10.0
#to reset the model variable
cumulative_product.reset_states()

huangapple
  • 本文由 发表于 2023年5月28日 03:12:31
  • 转载请务必保留本文链接:https://go.coder-hub.com/76348599.html
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定