This operation computes the classification error.
classification_error(output_vector, target_vector, axis = -1, topN = 1, name = "")
| output_vector | the output values of the network |
|---|---|
| target_vector | one-hot encoding of target values |
| axis | integer for axis along which the classification error is computed |
| topN | integer |
| name | string (optional) the name of the Function instance in the network |
It finds the index of the highest value in the output_vector and compares it to the actual ground truth label (the index of the hot bit in the target vector).
The result is a scalar (i.e., one by one matrix). This is often used as an evaluation criterion.
It cannot be used as a training criterion though since the gradient is not defined for it.
https://www.cntk.ai/pythondocs/cntk.metrics.html#cntk.metrics.classification_error