Python TensorFlow/TFLearn：ValueError：无法为 Tensor u'target/Y:0' 提供形状 (64,) 的值，其形状为 '(?, 10)'

TensorFlow/TFLearn: ValueError: Cannot feed value of shape (64,) for Tensor u'target/Y:0', which has shape '(?, 10)'

提问by user728785

I have been trying to perform regression using tflearnand my own dataset.

我一直在尝试使用tflearn和我自己的数据集进行回归。

Using tflearn I have been trying to implement a convolutional network based off an exampleusing the MNIST dataset. Instead of using the MNIST dataset I have tried replacing the training and test data with my own. My data is read in from a csv file and is a different shape to the MNIST data. I have 255 features which represent a 15*15 grid and a target value. In the example I replaced the lines 24-30 with (and included import numpy as np):

使用 tflearn，我一直在尝试基于使用 MNIST 数据集的示例来实现卷积网络。我没有使用 MNIST 数据集，而是尝试用我自己的数据替换训练和测试数据。我的数据是从 csv 文件中读入的，与 MNIST 数据的形状不同。我有 255 个特征，它们代表一个 15*15 的网格和一个目标值。在示例中，我将第 24-30 行替换为（并包含 import numpy as np）：

#read in train and test csv's where there are 255 features (15*15) and a target
csvTrain = np.genfromtxt('train.csv', delimiter=",")
X = np.array(csvTrain[:, :225]) #225, 15
Y = csvTrain[:,225]

csvTest = np.genfromtxt('test.csv', delimiter=",")
testX = np.array(csvTest[:, :225])
testY = csvTest[:,225]

#reshape features for each instance in to 15*15, targets are just a single number
X = X.reshape([-1,15,15,1])
testX = testX.reshape([-1,15,15,1])

## Building convolutional network
network = input_data(shape=[None, 15, 15, 1], name='input')

I get the following error:

我收到以下错误：

ValueError: Cannot feed value of shape (64,) for Tensor u'target/Y:0', which has shape '(?, 10)'

ValueError: 无法为 Tensor u'target/Y:0' 提供形状 (64,) 的值，其形状为 '(?, 10)'

I have tried various combinations and have seen a similar questionin stackoverflow but have not had success. The example in this page does not work for me and throws a similar error and I do not understand the answer provided or those provided by similar questions.

我尝试了各种组合，并在 stackoverflow 中看到了类似的问题，但没有成功。此页面中的示例对我不起作用并引发类似错误，我不明白所提供的答案或类似问题提供的答案。

How do I use my own data?

我如何使用我自己的数据？

回答by Olivier Moindrot

Short answer

简答

In the line 41 of the MNIST example, you also have to change the output size 10 to 1 in network = fully_connected(network, 10, activation='softmax')to network = fully_connected(network, 1, activation='linear'). Note that you can remove the final softmax.

在MNIST 示例的第 41 行中，您还必须将输出大小 10 更改为 1 in network = fully_connected(network, 10, activation='softmax')to network = fully_connected(network, 1, activation='linear')。请注意，您可以删除最终的 softmax。

Looking at your code, it seems you have a target value Y, which means using the L2 losswith mean_square(you will find hereall the losses available):

看你的代码，看来你有一个目标值Y，其使用的手段L2损失与mean_square（你会发现这里的一切损失提供）：

regression(network, optimizer='adam', learning_rate=0.01,
                 loss='mean_square', name='target')

Also, reshape Y and Y_test to have shape (batch_size, 1).

此外，重塑 Y 和 Y_test 以具有形状 (batch_size, 1)。

---

---

Long answer: How to analyse the error and find the bug

长答案：如何分析错误并找到错误

Here is how to analyse the error:

以下是分析错误的方法：

• The error is Cannot feed value ... for Tensor 'target/Y', which means it comes from the feed_dictargument Y.
• Again, according to the error, you try to feed an Y value of shape (64,)whereas the network expect a shape (?, 10).
  • It expects a shape (batch_size, 10), because originally it's a network for MNIST (10 classes)
• We now want to change the expected value of the network for Y.
  • in the code, we see that the last layer fully_connected(network, 10, activation='softmax')is returning an output of size 10
  • We change that to an output of size 1 without softmax: fully_connected(network, 1, activation='linear')

• 错误是Cannot feed value ... for Tensor 'target/Y'，这意味着它来自feed_dict参数 Y。
• 同样，根据错误，您尝试提供 Y 值，of shape (64,)而网络期望提供 shape (?, 10)。
  • 它需要一个形状 (batch_size, 10)，因为它最初是一个用于 MNIST（10 个类）的网络
• 我们现在想要改变 Y 的网络期望值。
  • 在代码中，我们看到最后一层fully_connected(network, 10, activation='softmax')正在返回大小为 10 的输出
  • 我们将其更改为没有 softmax 的大小为 1 的输出： fully_connected(network, 1, activation='linear')

In the end, it was not a bug, but a wrong model architecture.

最后，这不是错误，而是错误的模型架构。