Tensor to classification
Given a tensor representing classification results, outputs the indices of accepted classes and the corresponding tensor values.
- An input tensor of confidence values in which at most one dimension differs from one. The tool will reshape the tensor to a 1-by-N matrix.
- The minimum confidence value that will be accepted. Set to zero to accept all values.
- The maximum number of accepted results. Set to one to pick only the entry with the greatest confidence.
- The indices of selected entries as a N-by-1 matrix.
- The corresponding confidence values in the input tensor, sorted in descending order.