typedef struct {
const char *label;
float value;
} ei_impulse_result_classification_t;
Brief: Holds a particular class's label and the associated confidence score after running inference
Location: edge-impulse-sdk/classifier/ei_classifier_types.h
Description:
When performing inference for a classification task, the output of the model is given as a confidence score for each of the possible classes. Assuming the softmax function is used as the final layer in the model, each score must be between [0.0..1.0] and the sum of all the scores must equal 1.0.
ei_impulse_result_classification_t
holds the label and confidence score for each class after inference is performed. The results of inference will be an array of ei_impulse_result_classification_t
structs with EI_CLASSIFIER_LABEL_COUNT
elements.
Members:
label
- Pointer to a character array describing the associated class of the given bounding box. Taken from one of the elements ofei_classifier_inferencing_categories[]
.value
- Confidence score that the input raw data belongs to the given class.
Example:
https://github.com/edgeimpulse/example-standalone-inferencing/blob/master/source/main.cpp