TensorFlow / TFLearn：ValueError：无法为形状为（（？，10）'的Tensor u'target / Y：0'输入形状（64，）的值 [英] TensorFlow/TFLearn: ValueError: Cannot feed value of shape (64,) for Tensor u'target/Y:0', which has shape '(?, 10)'

问题描述

我一直在尝试使用 tflearn 和我自己的数据集进行回归。

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

我使用tflearn尝试基于示例（使用MNIST数据集）。我没有使用MNIST数据集，而是尝试用自己的数据替换训练和测试数据。我的数据是从csv文件读取的，与MNIST数据的形状不同。我有255个要素，它们代表15 * 15的网格和目标值。在示例中，我将第24-30行替换为（并将numpy导入为np）：

Using tflearn I have been trying to implement a convolutional network based off an example using 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):

#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')

我收到以下错误：

ValueError：无法输入形状值（64， ）对于Tensor u'target / Y：0'，形状为（（？，10）'的

I尝试过各种组合nd看到了一个类似的问题，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，并且我不理解所提供的答案或类似问题所提供的答案。

I have tried various combinations and have seen a similar question in 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.

如何使用我的

推荐答案

简短答案

在第41行中 MNIST示例，您还必须更改输出在 network = fully_connected（network，10，activation ='softmax'）到 network = fully_connected（network，1，Activation ='线性）。请注意，您可以删除最终的softmax。

Short answer

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.

看一下代码，看来您的目标值是 Y ，这意味着将 L2损失与 mean_square 一起使用（您会发现此处所有可能的损失）：

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

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

也请重塑Y和Y_test以使其具有形状（batch_size，1）。

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

以下是分析错误的方法：

Here is how to analyse the error:

• 错误是无法为Tensor'target / Y'馈入值...，这意味着它来自 feed_dict 自变量Y


• 同样，根据错误，您尝试输入形状为（64，）的Y值，而网络k期望形状为（?, 10）。
  
  
  
  
  • 它需要一个形状（batch_size，10），因为它最初是MNIST（10个类）的网络
  
  
  • The error is Cannot feed value ... for Tensor 'target/Y', which means it comes from the feed_dict argument 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)
    
    
    • 最后一层 fully_connected（network，10，activation ='softmax'）返回大小为10的输出
    
    
    • 我们将其更改为到大小为1且没有softmax的输出： fully_connected（network，1，activation ='linear'）
    
    
    • 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')

    最后，这不是错误，而是错误的模型架构。

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

    这篇关于TensorFlow / TFLearn：ValueError：无法为形状为（（？，10）'的Tensor u'target / Y：0'输入形状（64，）的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！