【发布时间】:2017-08-09 05:37:28
【问题描述】:
有人应该添加“net#”作为标签。我正在尝试通过使用本教程将其转变为卷积神经网络来改进我在 Azure 机器学习工作室中的神经网络:
https://gallery.cortanaintelligence.com/Experiment/Neural-Network-Convolution-and-pooling-deep-net-2
我的和本教程之间的区别在于我使用 35 个特征和 1 个标签进行回归,而他们使用 28x28 特征和 10 个标签进行分类。
我从基本示例和第二个示例开始,让他们使用:
input Data [35];
hidden H1 [100]
from Data all;
hidden H2 [100]
from H1 all;
output Result [1] linear
from H2 all;
现在我误解了对卷积的转换。在此处的教程和文档中:https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-azure-ml-netsharp-reference-guide 它没有提到如何为隐藏层计算节点元组值。教程说:
hidden C1 [5, 12, 12]
from Picture convolve {
InputShape = [28, 28];
KernelShape = [ 5, 5];
Stride = [ 2, 2];
MapCount = 5;
}
hidden C2 [50, 4, 4]
from C1 convolve {
InputShape = [ 5, 12, 12];
KernelShape = [ 1, 5, 5];
Stride = [ 1, 2, 2];
Sharing = [ F, T, T];
MapCount = 10;
}
似乎 [5, 12, 12] 和 [50,4,4] 与 KernalShape、Stride 和 MapCount 一起突然出现。我怎么知道哪些值对我的示例有效?我尝试使用相同的值,但它不起作用,我有一种感觉,因为他有一个 [28,28] 输入,而我有一个 [35],我需要 2 个整数而不是 3 的元组。
我刚刚尝试了似乎与教程相关的随机值:
const { T = true; F = false; }
input Data [35];
hidden C1 [7, 23]
from Data convolve {
InputShape = [35];
KernelShape = [7];
Stride = [2];
MapCount = 7;
}
hidden C2 [200, 6]
from C1 convolve {
InputShape = [ 7, 23];
KernelShape = [ 1, 7];
Stride = [ 1, 2];
Sharing = [ F, T];
MapCount = 14;
}
hidden H3 [100]
from C2 all;
output Result [1] linear
from H3 all;
目前似乎无法调试,因为 Azure 机器学习工作室给出的唯一错误代码是:
Exception":{"ErrorId":"LibraryException","ErrorCode":"1000","ExceptionType":"ModuleException","Message":"Error 1000: TLC library exception: Exception of type 'Microsoft.Numerics.AFxLibraryException' was thrown.","Exception":{"Library":"TLC","ExceptionType":"LibraryException","Message":"Exception of type 'Microsoft.Numerics.AFxLibraryException' was thrown."}}}Error: Error 1000: TLC library exception: Exception of type 'Microsoft.Numerics.AFxLibraryException' was thrown. Process exited with error code -2
感谢您的帮助!
【问题讨论】:
标签: machine-learning convolution azure-machine-learning-studio net#