apache-spark - Apache SystemML 标量矩阵(元素方面)乘法不起作用

Question

请考虑以下代码:

  #update
  W1 = W1 - learningRate * dJdW1
  W2 = W2 - learningRate * dJdW2

其中learningRate是double和dJdW1/dJdW1 2d矩阵。

我收到此错误:

ERROR: Runtime error in program block generated from statement block between lines 58 and 61 -- Error evaluating instruction: CP\xb0-*\xb0W2\xb7MATRIX\xb7DOUBLE\xb01.0E-5\xb7SCALAR\xb7DOUBLE\xb7true\xb0dJdW2\xb7MATRIX\xb7DOUBLE\xb0_mVar117\xb7MATRIX\xb7DOUBLE

编辑 12.7.17:

加上这个...

ordinal not in range(128)'))

整个DML可以找到here

完整的错误可以在 here 找到

整个 jupyther 笔记本可以找到 here

Answer 1

单元格标量矩阵运算很好。查看您的错误，它表明您的矩阵/向量维度不兼容:

 : Block sizes are not matched for binary cell operations: 3x1 vs 2x3
 org.apache.sysml.runtime.matrix.data.MatrixBlock.binaryOperations(MatrixBlock.java:2872)
 org.apache.sysml.runtime.instructions.cp.PlusMultCPInstruction.processInstruction(PlusMultCPInstruction.java:66)
 org.apache.sysml.runtime.controlprogram.ProgramBlock.executeSingleInstruction(ProgramBlock.java:290)

查看您的笔记本，它来自:

 W2 = W2 - learningRate * dJdW2

W2 已初始化 W2 = rand(rows=hiddenLayerSize,cols=outputLayerSize) 作为 3x1 矩阵，而 dJDW2 是 2x3 矩阵。