如何使张量流模型将列表作为输入？

Question

我是 tensorflow 的新手，我正在制作一个可以进行乘法运算的 AI，

我需要制作它以便我的模型可以将列表作为输入。

这是我的代码：

import tensorflow as tf

import numpy as np

import matplotlib.pyplot as plt

multiplication_q = np.array([[10,10],[1,1],[2,2],[0,0],[3,3],[4,4],[5,5],[6,6],[7,7],[8,8],[9,9],[1,0],[11,10],[27,0],[30,2],[4,3],[17,22],[20,0],[8,13],[21,4],[19,24],[11,19],[8,2],[4,5],[11,11],[1,15],[2,12],[15,3],[18,0],[49,7],[5,7],[12,4]], dtype=object)

multiplication_a = np.array([100,1,4,0,9,16,25,36,49,64,96,0,110,0,60,12,374,0,104,84,456,209,16,20,121,15,24,45,0,343,35,48], dtype=float)

model = tf.keras.Sequential([

  tf.keras.layers.Dense(units=4, input_shape=[1]),

  tf.keras.layers.Dense(units=4),

  tf.keras.layers.Dense(units=1)

])

model.compile(loss='mean_squared_error', optimizer=tf.keras.optimizers.Adam(0.1))

history = model.fit(multiplication_q, multiplication_a, epochs=750, verbose=False)

print(model.predict([4, 5]))

这是错误消息：

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function  *

        return step_function(self, iterator)

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function  **

        outputs = model.distribute_strategy.run(run_step, args=(data,))

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run

        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica

        return self._call_for_each_replica(fn, args, kwargs)

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica

        return fn(*args, **kwargs)

Answer 1

要解决您的问题，您应该做三件事：1- 将dtypefrom更改为这样multiplication_q：objectintmultiplication_q = np.array([[10,10],[1,1],[2,2],[0,0],[3,3],[4,4],[5,5],[6,6],[7,7],[8,8],[9,9],[1,0],[11,10],[27,0],[30,2],[4,3],[17,22],[20,0],[8,13],[21,4],[19,24],[11,19],[8,2],[4,5],[11,11],[1,15],[2,12],[15,3],[18,0],[49,7],[5,7],[12,4]], dtype=int)2- 在模型的第一个 Dense 层中使用input_shape=(2,)而不是input_shape=[1]，如下所示：model = tf.keras.Sequential([   tf.keras.layers.Dense(units=4, input_shape=(2,)),   tf.keras.layers.Dense(units=4),   tf.keras.layers.Dense(units=1) ])3- 对于预测函数，你应该传递一个listoflist而不是 a ，因为你用oflist进行了训练listlistmodel.predict([[4, 5]])

Answer 2

尝试将第一个密集层中的输入设置为，将输入multiplication_q.shape形状设置为132, 2编辑：下面的代码解决了您的问题，尽管您将不得不尝试一些东西，因为它不是很准确。import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltmultiplication_q = np.asarray([[10,10],[1,1],[2,2],[0,0],[3,3],[4,4],[5,5],[6,6],[7,7],[8,8],[9,9],[1,0],[11,10],[27,0],[30,2],[4,3],[17,22],[20,0],[8,13],[21,4],[19,24],[11,19],[8,2],[4,5],[11,11],[1,15],[2,12],[15,3],[18,0],[49,7],[5,7],[12,4]])multiplication_a = np.asarray([100,1,4,0,9,16,25,36,49,64,96,0,110,0,60,12,374,0,104,84,456,209,16,20,121,15,24,45,0,343,35,48])multiplication_q = multiplication_q/np.amax(multiplication_q)multiplication_a = multiplication_a/np.amax(multiplication_a)model = tf.keras.models.Sequential()model.add(tf.keras.Input(shape=(2, )))model.add(tf.keras.layers.Dense(32, activation='relu'))model.add(tf.keras.layers.Dense(units=1))model.compile(loss='mean_squared_error', optimizer=tf.keras.optimizers.Adam(0.1))history = model.fit(multiplication_q, multiplication_a, epochs=750)print(model.predict(np.asarray([[4, 5]])/np.amax(multiplication_q)*np.amax(multiplication_a)))