ValueError:具有形状 (3,1) 的不可广播输出操作数与广播形状 (3,4) 不匹配 [英] ValueError: non-broadcastable output operand with shape (3,1) doesn't match the broadcast shape (3,4)

问题描述

我最近开始在 YouTube 上学习 Siraj Raval 的深度学习教程，但是当我尝试运行我的代码时出现错误.代码来自他的系列的第二集，如何制作神经网络.当我运行代码时出现错误:

回溯(最近一次调用最后一次):文件C:UsersdpoppDocumentsMachine Learningfirst_neural_net.py"，第 66 行，在 <module> 中.神经网络.训练(training_set_inputs，training_set_outputs，10000)文件C:UsersdpoppDocumentsMachine Learningfirst_neural_net.py"，第 44 行，火车中self.synaptic_weights += 调整ValueError:具有形状 (3,1) 的不可广播输出操作数与广播形状 (3,4) 不匹配

我用他的代码检查了多次，没有发现任何差异，甚至尝试从 GitHub 链接复制和粘贴他的代码.这是我现在拥有的代码:

from numpy import exp, array, random, dot类神经网络():def __init__(self):# 种子随机数生成器，所以它生成相同的数字# 每次程序运行时.随机种子(1)# 我们对单个神经元进行建模，具有 3 个输入连接和 1 个输出连接.# 我们将随机权重分配给一个 3 x 1 矩阵，其值在 -1 到 1 的范围内# 并表示 0.self.synaptic_weights = 2 * random.random((3, 1)) - 1# Sigmoid 函数，描述 S 形曲线.# 我们通过这个函数将输入的加权和传递给# 在 0 和 1 之间将它们归一化.def __sigmoid(self, x):返回 1/(1 + exp(-x))# Sigmoid 函数的导数.# 这是 Sigmoid 曲线的梯度.# 它表明我们对现有权重的信心.def __sigmoid_derivative(self, x):返回 x * (1 - x)# 我们通过反复试验来训练神经网络.# 每次调整突触权重.def train(self, training_set_inputs, training_set_outputs, number_of_training_iterations):对于范围内的迭代(number_of_training_iterations):# 通过我们的神经网络(单个神经元)传递训练集.输出 = self.think(training_set_inputs)# 计算误差(期望输出之间的差异# 和预测输出).错误 = training_set_outputs - 输出# 将误差乘以输入，再乘以 Sigmoid 曲线的梯度.# 这意味着更不自信的权重被调整得更多.# 这意味着输入为零，不会导致权重发生变化.调整 = 点(training_set_inputs.T，错误 * self.__sigmoid_derivative(输出))# 调整权重.self.synaptic_weights += 调整# 神经网络思考.定义思考(自我，输入):# 通过我们的神经网络(我们的单个神经元)传递输入.返回 self.__sigmoid(dot(inputs, self.synaptic_weights))如果 __name__ == '__main__':# 初始化单个神经元神经网络神经网络 = 神经网络()print("随机起始突触权重:")打印(neural_network.synaptic_weights)# 训练集.我们有 4 个示例，每个示例由 3 个输入值组成# 和 1 个输出值.training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])training_set_outputs = 数组([[0, 1, 1, 0]])# 使用训练集训练神经网络# 做 10,000 次，每次做小调整神经网络.训练(training_set_inputs，training_set_outputs，10000)打印(训练后的新突触权重:")打印(neural_network.synaptic_weights)# 在新情况下测试神经网络print("考虑新情况 [1, 0, 0] -> ?:")打印(neural_network.think(数组([[1, 0, 0]])))

即使复制并粘贴了在 Siraj 的剧集中工作的相同代码，我仍然遇到同样的错误.

我刚开始研究人工智能，不明白错误意味着什么.有人可以解释一下这是什么意思以及如何解决吗?谢谢！

解决方案

将self.synaptic_weights += adjust改为

self.synaptic_weights = self.synaptic_weights + 调整

<小时>

self.synaptic_weights 的形状必须为 (3,1)，而 adjustment 的形状必须为 (3,4).虽然形状是可广播 numpy一定不喜欢尝试将形状为 (3,4) 的结果分配给形状为 (3,1) 的数组

a = np.ones((3,1))b = np.random.randint(1,10, (3,4))>>>一种数组([[1],[1],[1]])>>>乙数组([[8, 2, 5, 7],[2, 5, 4, 8],[7, 7, 6, 6]])>>>a + b数组([[9, 3, 6, 8],[3, 6, 5, 9],[8, 8, 7, 7]])>>>b += a>>>乙数组([[9, 3, 6, 8],[3, 6, 5, 9],[8, 8, 7, 7]])>>>一种数组([[1],[1],[1]])>>>a += b回溯(最近一次调用最后一次):文件<pyshell#24>"，第 1 行，在 <module> 中a += bValueError:具有形状 (3,1) 的不可广播输出操作数与广播形状 (3,4) 不匹配

使用 numpy 时会出现同样的错误.添加并指定a作为输出数组

<预><代码>>>>np.add(a,b, out = a)回溯(最近一次调用最后一次):文件<pyshell#31>"，第 1 行，在 <module> 中np.add(a,b, out = a)ValueError:具有形状 (3,1) 的不可广播输出操作数与广播形状 (3,4) 不匹配>>>

需要创建一个新的a

<预><代码>>>>a = a + b>>>一种数组([[10, 4, 7, 9],[ 4, 7, 6, 10],[ 9, 9, 8, 8]])>>>

I recently started to follow along with Siraj Raval's Deep Learning tutorials on YouTube, but I an error came up when I tried to run my code. The code is from the second episode of his series, How To Make A Neural Network. When I ran the code I got the error:

Traceback (most recent call last):
File "C:UsersdpoppDocumentsMachine Learningfirst_neural_net.py", line 66, in <module>
neural_network.train(training_set_inputs, training_set_outputs, 10000)
File "C:UsersdpoppDocumentsMachine Learningfirst_neural_net.py", line 44, in train
self.synaptic_weights += adjustment
ValueError: non-broadcastable output operand with shape (3,1) doesn't match the broadcast shape (3,4)

I checked multiple times with his code and couldn't find any differences, and even tried copying and pasting his code from the GitHub link. This is the code I have now:

from numpy import exp, array, random, dot

class NeuralNetwork():
    def __init__(self):
        # Seed the random number generator, so it generates the same numbers
        # every time the program runs.
        random.seed(1)

        # We model a single neuron, with 3 input connections and 1 output connection.
        # We assign random weights to a 3 x 1 matrix, with values in the range -1 to 1
        # and mean 0.
        self.synaptic_weights = 2 * random.random((3, 1)) - 1

    # The Sigmoid function, which describes an S shaped curve.
    # We pass the weighted sum of the inputs through this function to
    # normalise them between 0 and 1.
    def __sigmoid(self, x):
        return 1 / (1 + exp(-x))

    # The derivative of the Sigmoid function.
    # This is the gradient of the Sigmoid curve.
    # It indicates how confident we are about the existing weight.
    def __sigmoid_derivative(self, x):
        return x * (1 - x)

    # We train the neural network through a process of trial and error.
    # Adjusting the synaptic weights each time.
    def train(self, training_set_inputs, training_set_outputs, number_of_training_iterations):
        for iteration in range(number_of_training_iterations):
            # Pass the training set through our neural network (a single neuron).
            output = self.think(training_set_inputs)

            # Calculate the error (The difference between the desired output
            # and the predicted output).
            error = training_set_outputs - output

            # Multiply the error by the input and again by the gradient of the Sigmoid curve.
            # This means less confident weights are adjusted more.
            # This means inputs, which are zero, do not cause changes to the weights.
            adjustment = dot(training_set_inputs.T, error * self.__sigmoid_derivative(output))

            # Adjust the weights.
            self.synaptic_weights += adjustment

    # The neural network thinks.
    def think(self, inputs):
        # Pass inputs through our neural network (our single neuron).
        return self.__sigmoid(dot(inputs, self.synaptic_weights))

if __name__ == '__main__':

    # Initialize a single neuron neural network
    neural_network = NeuralNetwork()

    print("Random starting synaptic weights:")
    print(neural_network.synaptic_weights)

    # The training set. We have 4 examples, each consisting of 3 input values
    # and 1 output value.
    training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
    training_set_outputs = array([[0, 1, 1, 0]])

    # Train the neural network using a training set
    # Do it 10,000 times and make small adjustments each time
    neural_network.train(training_set_inputs, training_set_outputs, 10000)

    print("New Synaptic weights after training:")
    print(neural_network.synaptic_weights)

    # Test the neural net with a new situation
    print("Considering new situation [1, 0, 0] -> ?:")
    print(neural_network.think(array([[1, 0, 0]])))

Even after copying and pasting the same code that worked in Siraj's episode, I'm still getting the same error.

I just started out look into artificial intelligence, and don't understand what the error means. Could someone please explain what it means and how to fix it? Thanks!

解决方案

Change self.synaptic_weights += adjustment to

self.synaptic_weights = self.synaptic_weights + adjustment

---

self.synaptic_weights must have a shape of (3,1) and adjustment must have a shape of (3,4). While the shapes are broadcastable numpy must not like trying to assign the result with shape (3,4) to an array of shape (3,1)

a = np.ones((3,1))
b = np.random.randint(1,10, (3,4))

>>> a
array([[1],
       [1],
       [1]])
>>> b
array([[8, 2, 5, 7],
       [2, 5, 4, 8],
       [7, 7, 6, 6]])

>>> a + b
array([[9, 3, 6, 8],
       [3, 6, 5, 9],
       [8, 8, 7, 7]])

>>> b += a
>>> b
array([[9, 3, 6, 8],
       [3, 6, 5, 9],
       [8, 8, 7, 7]])
>>> a
array([[1],
       [1],
       [1]])

>>> a += b
Traceback (most recent call last):
  File "<pyshell#24>", line 1, in <module>
    a += b
ValueError: non-broadcastable output operand with shape (3,1) doesn't match the broadcast shape (3,4)

The same error occurs when using numpy.add and specifying a as the output array

>>> np.add(a,b, out = a)
Traceback (most recent call last):
  File "<pyshell#31>", line 1, in <module>
    np.add(a,b, out = a)
ValueError: non-broadcastable output operand with shape (3,1) doesn't match the broadcast shape (3,4)
>>> 

A new a needs to be created

>>> a = a + b
>>> a
array([[10,  4,  7,  9],
       [ 4,  7,  6, 10],
       [ 9,  9,  8,  8]])
>>> 

这篇关于ValueError:具有形状 (3,1) 的不可广播输出操作数与广播形状 (3,4) 不匹配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！