Illustrated C/C++ source sheets, symbol index, API relationship graph, compiler console and debug trace

LIVE AI / FLEXIBLE SENSING / FLIGHT CONTEXT

Sensoraia API

Live AI and sensing, connected to the flight.
See, listen, inspect and return supported results while airborne.

Loading...
Searching...
No Matches
inference_worker.c File Reference

Persistent saved-picture inference with explicit request correlation and module-owned results. More...

#include "inference_worker.h"
#include <errno.h>
#include <stdio.h>
#include <string.h>
Include dependency graph for inference_worker.c:

Go to the source code of this file.

Functions

static bool analyze_image (struct inference_context *context, const struct inference_image_processor *processor, const char *image, uint32_t sequence, char *error, size_t capacity)
 Publish a result only after complete preparation and execution for this picture.
static bool open_fallback_onnx (struct inference_context *context, struct inference_settings *settings, const struct inference_image_processor *processor, char *error, size_t capacity)
 Probe sibling INT8 then FP32 ONNX exports when automatic settings point to an RPK or unsupported INT8 graph.
int inference_worker_cli (int argc, char **argv, const struct inference_image_processor *processor)
 Dispatch one-shot analysis, model checks or the persistent ANALYZE protocol.

Detailed Description

Persistent saved-picture inference with explicit request correlation and module-owned results.

No sensor is acquired here; simulated and real saved images enter the same model path.

Definition in file inference_worker.c.

Function Documentation

◆ analyze_image()

bool analyze_image ( struct inference_context * context,
const struct inference_image_processor * processor,
const char * image,
uint32_t sequence,
char * error,
size_t capacity )
static

Publish a result only after complete preparation and execution for this picture.

Definition at line 28 of file inference_worker.c.

◆ inference_worker_cli()

int inference_worker_cli ( int argc,
char ** argv,
const struct inference_image_processor * processor )

Dispatch one-shot analysis, model checks or the persistent ANALYZE protocol.

Parameters
argcArgument count including the executable.
argvBorrowed command-line tokens; diagnostics use stderr, protocol replies stdout.
processorModule contract whose callback/context lifetimes cover this call.
Returns
Minus one when this mode was not selected, zero on success, one on failure, two on misuse.
Note
Request numbers increase within a server lifetime to prevent stale reply association.

Definition at line 75 of file inference_worker.c.

◆ open_fallback_onnx()

bool open_fallback_onnx ( struct inference_context * context,
struct inference_settings * settings,
const struct inference_image_processor * processor,
char * error,
size_t capacity )
static

Probe sibling INT8 then FP32 ONNX exports when automatic settings point to an RPK or unsupported INT8 graph.

Definition at line 38 of file inference_worker.c.