Neural network 用于图像分类的Encog神经网络:训练

Neural network 用于图像分类的Encog神经网络:训练,neural-network,encog,Neural Network,Encog,我在训练用于图像分类的神经网络时遇到了问题。基于神经网络的性能,它似乎没有学习 我基本上是在encog示例(ImageNeuralNetwork)中运行给定的程序来对一组图像进行分类。以下是示例程序输出 Training set created Added input image:./faces/at33_straight_neutral_open.png; identity: shadesNone Added input image:./faces/night/night_up_happy_s

我在训练用于图像分类的神经网络时遇到了问题。基于神经网络的性能,它似乎没有学习

我基本上是在encog示例(ImageNeuralNetwork)中运行给定的程序来对一组图像进行分类。以下是示例程序输出

Training set created
Added input image:./faces/at33_straight_neutral_open.png; identity: shadesNone
Added input image:./faces/night/night_up_happy_sunglasses_4.png; identity: shades
...<more files here>...
Added input image:./faces/cheyer/cheyer_up_neutral_open_4.png; identity: shadesNone
Downsampling images...
Created network: [BasicNetwork: Layers=3]
Training Beginning... Output patterns=2
Beginning training...
Iteration #1 Error:199.591952% elapsed time = 00:00:00 time left = 00:01:00
Iteration #2 Error:196.384178% elapsed time = 00:00:00 time left = 00:01:00
Iteration #3 Error:160.422574% elapsed time = 00:00:00 time left = 00:01:00
...
Iteration #16 Error:99.733657% elapsed time = 00:00:00 time left = 00:01:00
...
Iteration #202 Error:99.489796% elapsed time = 00:00:04 time left = 00:01:00
...
Iteration #203 Error:199.605091% elapsed time = 00:00:04 time left = 00:01:00
顺便说一句,我不能正确运行森林覆盖率示例(需要输入文件),而我可以运行月球着陆器和XOR示例(不需要输入文件)。这加强了我的假设,即我的问题与目录相关


非常感谢您的帮助。谢谢。

似乎是3.2.0的bug,有同样的问题
尝试使用3.1.0来训练网络,应该可以修复它

忽略我上面的帖子,3.2.0工作正常

我也遇到了同样的问题,比如新的问题27,网络似乎什么也学不到,错误的改变变得疯狂。在做了更多的研究之后,我发现encog有点讨厌白色太多的图片

对我有效的解决方案是降低用于网络学习的图片的亮度。实现这一点的一种方法(在过程中不破坏原始图像)是将RescaleOp类与BuffereImage一起使用

其他可能(未经测试)的解决方案可能是在学习过程中改变向网络反馈的图像的顺序

CreateTraining: width:16,height:15,type:Brightness
Input: image:./faces/at33_straight_neutral_open.png, identity:shadesNone
Input: image:./faces/night/night_up_happy_sunglasses_4.png, identity:shades
Input: image:./faces/choon/choon_up_angry_open_4.png, identity:shadesNone
Input: image:./faces/cheyer/cheyer_left_angry_sunglasses_4.png, identity:shades
<more files...>
Network: hidden1:10, hidden2:10
Train: Mode:console, Minutes:1, StrategyError:0.25, StrategyCycles:100 
Whatis: image:./faces/tammo/tammo_right_sad_sunglasses_4.png
<more files...>
  Classpath Tab
    Bootstrap Entries
      JRE System Library [jre7]
    User Entries
        encog-examples (default classpath)
          encog-examples
          encog-core-3.2.0-SNAPSHOT.jar \encog-examples\lib