HomeGuidesProjectsForum

ei_impulse_result_timing_t

typedef struct {
    int sampling;
    int dsp;
    int classification;
    int anomaly;
    int64_t dsp_us;
    int64_t classification_us;
    int64_t anomaly_us;
} ei_impulse_result_timing_t;

Brief: Holds timing information about the preprocessing (DSP) and inference blocks.

Location: edge-impulse-sdk/classifier/ei_classifier_types.h

Description:
Records timing information during the execution of the preprocessing (DSP) and inference blocks. Can be used to determine if inference will meet timing requirements on your particular platform.

Members:

  • sampling - If using run_impulse() to perform sampling and inference, it is the amount of time (in milliseconds) it took to fetch raw samples. Not used for run_classifier().
  • dsp - Amount of time (in milliseconds) it took to run the preprocessing (DSP) block.
  • classification - Amount of time (in milliseconds) it took to run the inference block.
  • anomaly - Amount of time (in milliseconds) it took to run anomaly detection. Valid only if EI_CLASSIFIER_HAS_ANOMALY == 1.
  • dsp_us - Amount of time (in microseconds) it took to run the preprocessing (DSP) block.
  • classification_us - Amount of time (in microseconds) it took to run the inference block.
  • anomaly_us - Amount of time (in microseconds) it took to run anomaly detection. Valid only if EI_CLASSIFIER_HAS_ANOMALY == 1.

Example:
https://github.com/edgeimpulse/example-standalone-inferencing/blob/master/source/main.cpp