Usage

Celantur SDK guide for model compilation and inference

Check out the SDK library reference and examples.

Example	What it demonstrates
onnx	Minimal CPU anonymisation with the ONNX inference engine, plus tuning inference settings such as thread count and optimisation level.
openvino	Compile and run a model with the OpenVINO CPU inference engine.
tensorrt	Compile and run a model on GPU with TensorRT, including precision and optimisation level.
cuda	Full GPU inference pipeline without copying image data back to the CPU.
tracking	Video processing with object tracking using a smaller model.
jpeg	Full CPU workflow: JPEG decode/encode with EXIF preservation, detection visualisation, per-class counts, and metric serialisation.

Workflow for model compilation

The default model is ONNX. You can transcompile the model to OpenVINO for better performance on Intel CPUs or TensorRT for better performance on NVIDIA GPUs.

For NVIDIA GPUs, you need to compile a new model for each type of GPU architecture.

1. Create instance of ModelCompiler

2. Get settings InferenceEnginePluginCompileSettings from ModelCompiler.preload_model(model_path);

3. Optional: Adjust settings InferenceEnginePluginCompileSettings

4. Execute model compilation with ModelCompiler.compile_mode()

Example code for TensorRT

#include "CelanturSDKInterface.h"
#include "CommonParameters.h"

// 1. Create instance of ModelCompiler
CelanturSDK::ModelCompilerParams compiler_params;
compiler_params.inference_plugin = "/usr/local/lib/libTensorRTRuntime.so";
CelanturSDK::ModelCompiler compiler("/path/to/license", compiler_params);

// 2. Get settings
celantur::InferenceEnginePluginCompileSettings settings = compiler.preload_model("/path/to/model.onnx.enc");

// 3. Adjust settings       
settings["precision"] = celantur::CompilePrecision::FP32;
settings["optimisation_level"] = celantur::OptimisationLevel::Low;

// 4. Compile model
compiler.compile_model(settings, model_path_compiled);

Workflow for inference and blurring

Initialise process engine

1. Create instance of Processor using the model.

2. Get InferenceEnginePluginSettings from Processor.get_inference_settings()

3. Optional: Adjust inference settings.

4. Load model with your adjusted settings.

Example Code

#include "CelanturSDKInterface.h"
#include "CommonParameters.h"

// 1. Create instance of Processor 
celantur::ProcessorParams params;
//    If you use TensorRT
params.inference_plugin = "/usr/local/lib/libTensorRTRuntime.so";
params.swapRB = true;
CelanturSDK::Processor processor(params, "/path/to/license");

// 2. Get settings.
celantur::InferenceEnginePluginSettings settings = processor.get_inference_settings(model_path_compiled);

// 4. Load the compiled inference model.
processor.load_inference_model(settings);

Run inference and blurring

1. Run inference with Processor.process()

2. Get anonymised image with Processor.get_result()

3. Get detections with Processor.get_detections() (necessary step to remove item from queue).

Example Code

#include "CelanturSDKInterface.h"
#include "CelanturDetection.h"
#include <opencv2/opencv.hpp>

// Load image
cv::Mat image = cv::imread("/path/to/original/image");

// 5. Run inference
processor.process(image);

// 6. Get anonymised image
cv::Mat out = processor.get_result();

// 7. Get detections. Necessary to free up the memory.
processor.get_detections();

// Save the image
cv::imwrite("/path/to/anonymised/image", out);