Fix incorrect comment for output of argmax_ex in NeuralNetworksEx.h
- Output rank should be same rank with input
- Reduced axes are retained with length 1
Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
/**
* Find index with the largest value across axes of a input tensor.
*
- * Reduces the input tensor along the given dimensions to reduce.
+ * Reduces the input tensor along the given dimensions to reduce. The reduced
+ * dimensions are retained with length 1.
*
* Supported tensor {@link OperandCode}:
* * {@link ANEURALNETWORKS_TENSOR_FLOAT32}
*
* Outputs:
* * 0: A output tensor of {@link ANEURALNETWORKS_TENSOR_INT32}.
- * The rank of output tensor should be rank(input_tensor)-1.
+ * The rank of output tensor should be same rank of input0.
*/
ANEURALNETWORKS_ARGMAX_EX = 50015,