用于回归的tensorflow深度神经网络总是预测同一批次中的相同结果

Question

我使用张量流来实现用于回归的简单多层感知器。该代码是从标准mnist分类器修改的，我只将输出成本更改为MSE（使用tf.reduce_mean(tf.square(pred-y))）以及一些输入，输出大小设置。但是，如果我使用回归对网络进行训练，在几个时期之后，输出批次是完全相同的。例如：

target: 48.129, estimated: 42.634 
target: 46.590, estimated: 42.634 
target: 34.209, estimated: 42.634 
target: 69.677, estimated: 42.634 
...... 

我已经使用sklearn.preprocessing.scale尝试了不同的批量大小，不同的初始化，输入归一化（我的输入范围有很大的不同）。但是，他们都没有工作。我也试过了Tensorflow的一个sklearn例子（Deep Neural Network Regression with Boston Data）。但我在第40行另一个错误：

“模块”对象有没有属性“infer_real_valued_columns_from_input”

任何人有问题出在哪里的线索？谢谢

我的代码如下，可能会有点有点长，但很straghtforward：

from __future__ import absolute_import 
from __future__ import division 
from __future__ import print_function 

import tensorflow as tf 
from tensorflow.contrib import learn 
import matplotlib.pyplot as plt 

from sklearn.pipeline import Pipeline 
from sklearn import datasets, linear_model 
from sklearn import cross_validation 
import numpy as np 

boston = learn.datasets.load_dataset('boston') 
x, y = boston.data, boston.target 
X_train, X_test, Y_train, Y_test = cross_validation.train_test_split(
x, y, test_size=0.2, random_state=42) 

total_len = X_train.shape[0] 

# Parameters 
learning_rate = 0.001 
training_epochs = 500 
batch_size = 10 
display_step = 1 
dropout_rate = 0.9 
# Network Parameters 
n_hidden_1 = 32 # 1st layer number of features 
n_hidden_2 = 200 # 2nd layer number of features 
n_hidden_3 = 200 
n_hidden_4 = 256 
n_input = X_train.shape[1] 
n_classes = 1 

# tf Graph input 
x = tf.placeholder("float", [None, 13]) 
y = tf.placeholder("float", [None]) 

# Create model 
def multilayer_perceptron(x, weights, biases): 
    # Hidden layer with RELU activation 
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1']) 
    layer_1 = tf.nn.relu(layer_1) 

    # Hidden layer with RELU activation 
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2']) 
    layer_2 = tf.nn.relu(layer_2) 

    # Hidden layer with RELU activation 
    layer_3 = tf.add(tf.matmul(layer_2, weights['h3']), biases['b3']) 
    layer_3 = tf.nn.relu(layer_3) 

    # Hidden layer with RELU activation 
    layer_4 = tf.add(tf.matmul(layer_3, weights['h4']), biases['b4']) 
    layer_4 = tf.nn.relu(layer_4) 

    # Output layer with linear activation 
    out_layer = tf.matmul(layer_4, weights['out']) + biases['out'] 
    return out_layer 

# Store layers weight & bias 
weights = { 
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1], 0, 0.1)), 
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], 0, 0.1)), 
    'h3': tf.Variable(tf.random_normal([n_hidden_2, n_hidden_3], 0, 0.1)), 
    'h4': tf.Variable(tf.random_normal([n_hidden_3, n_hidden_4], 0, 0.1)), 
    'out': tf.Variable(tf.random_normal([n_hidden_4, n_classes], 0, 0.1)) 
} 
biases = { 
    'b1': tf.Variable(tf.random_normal([n_hidden_1], 0, 0.1)), 
    'b2': tf.Variable(tf.random_normal([n_hidden_2], 0, 0.1)), 
    'b3': tf.Variable(tf.random_normal([n_hidden_3], 0, 0.1)), 
    'b4': tf.Variable(tf.random_normal([n_hidden_4], 0, 0.1)), 
    'out': tf.Variable(tf.random_normal([n_classes], 0, 0.1)) 
} 

# Construct model 
pred = multilayer_perceptron(x, weights, biases) 

# Define loss and optimizer 
cost = tf.reduce_mean(tf.square(pred-y)) 
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) 

# Launch the graph 
with tf.Session() as sess: 
    sess.run(tf.initialize_all_variables()) 

    # Training cycle 
    for epoch in range(training_epochs): 
     avg_cost = 0. 
     total_batch = int(total_len/batch_size) 
     # Loop over all batches 
     for i in range(total_batch-1): 
      batch_x = X_train[i*batch_size:(i+1)*batch_size] 
      batch_y = Y_train[i*batch_size:(i+1)*batch_size] 
      # Run optimization op (backprop) and cost op (to get loss value) 
      _, c, p = sess.run([optimizer, cost, pred], feed_dict={x: batch_x, 
                  y: batch_y}) 
      # Compute average loss 
      avg_cost += c/total_batch 

     # sample prediction 
     label_value = batch_y 
     estimate = p 
     err = label_value-estimate 
     print ("num batch:", total_batch) 

     # Display logs per epoch step 
     if epoch % display_step == 0: 
      print ("Epoch:", '%04d' % (epoch+1), "cost=", \ 
       "{:.9f}".format(avg_cost)) 
      print ("[*]----------------------------") 
      for i in xrange(3): 
       print ("label value:", label_value[i], \ 
        "estimated value:", estimate[i]) 
      print ("[*]============================") 

    print ("Optimization Finished!") 

    # Test model 
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) 
    # Calculate accuracy 
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) 
    print ("Accuracy:", accuracy.eval({x: X_test, y: Y_test})) 

Answer 1

简短的回答：

使用tf.transpose(pred)移调您pred载体。

较长答案：

的问题是，pred（预测）和y（标签）是不一样的形状：一种是行向量和其它的列向量。显然，当你对它们应用一个元素明智的操作时，你会得到一个矩阵，这不是你想要的。

解决方法是使用tf.transpose()转置预测向量以获得适当的向量，从而获得适当的损失函数。实际上，如果您在示例中将批量大小设置为1，则即使没有修复，也会看到它的工作原理，因为转置1x1向量是无操作的。

我将此修复程序应用于您的示例代码并观察到以下行为。修复前：

Epoch: 0245 cost= 84.743440580 
[*]---------------------------- 
label value: 23 estimated value: [ 27.47437096] 
label value: 50 estimated value: [ 24.71126747] 
label value: 22 estimated value: [ 23.87785912] 

，并在同一时间点的修正后：

Epoch: 0245 cost= 4.181439120 
[*]---------------------------- 
label value: 23 estimated value: [ 21.64333534] 
label value: 50 estimated value: [ 48.76105118] 
label value: 22 estimated value: [ 24.27996063] 

你会看到，成本要低得多，它实际上是学到了价值50正确。你必须对学习速度做一些微调，这样当然会改善你的成绩。

Answer 2

有可能与您的数据集加载或索引执行的问题。如果您只修改了MSE的成本，请确保pred和y正确更新，并且您没有用不同的图表操作覆盖它们。

帮助调试的另一件事是预测实际的回归输出。它还将帮助，如果你贴得更你的代码，所以我们可以看到你的具体数据加载实施等