How can I optimize the ZED SDK AI models manually?

Last updated: October 22, 2026

The ZED SDK provides AI models for depth estimation (NEURAL LIGHT, NEURAL, and NEURAL PLUS depth modes), Object Detection and Tracking, and Human Body Detection and Tracking (skeleton tracking).

The AI models are not included in the installer of the ZED SDK because of their size, but they can be downloaded from our servers during the installation and optimized for the GPU available on the host device.

If you decide not to download and optimize the AI models during the installation of the ZED SDK, the process is performed automatically by the ZED SDK the first time that the required AI model is used.

There are situations where the AI models must be cleaned and optimized manually:

the GPU of the host device has been replaced;
the ZED SDK has been updated to a new version;
the download process failed for unexpected reasons (e.g. power outage, internet connection drop, etc.);
the optimization process stopped for unexpected reasons;
unexpected behavior of the ZED SDK processing (e.g. wrong depth map in NEURAL depth modes, wrong object detections, wrong skeleton detection, etc.).

Note: all the operations described below can also be performed from the graphical interface of the ZED Diagnostics tool by clicking on the AI MODELS button, available after completing a diagnostic test. See the ZED Diagnostics documentation. On headless devices (e.g. NVIDIA® Jetson™ without a display), add the -c option to run the tool in command-line mode.

How to run the commands

Open a shell console and run the tool with the option described in the table below.

Linux / NVIDIA® Jetson™ (the current folder is not relevant):
```
ZED_Diagnostic <option>
```
Windows (Command Prompt or PowerShell):
```
cd "C:\Program Files (x86)\ZED SDK\tools"
& ".\ZED Diagnostic.exe" <option>
```
In the Command Prompt (cmd.exe), omit the leading &: "ZED Diagnostic.exe" <option>

Replace <option> with one of the following:

Option	Operation
`-aic`	Clean (remove) all the downloaded and optimized AI models; useful to free up disk space or to reset the optimizations if something is not working properly
`-nrlo_light`	Download and optimize the NEURAL LIGHT depth model
`-nrlo`	Download and optimize the NEURAL depth model
`-nrlo_plus`	Download and optimize the NEURAL PLUS depth model
`-nrlo_all`	Download and optimize all the AI-based depth models
`-ais X`	Download and optimize a single AI model (see the list below)
`-aid`	Download all the AI models without optimizing them (useful to prepare an offline deployment; the optimization is performed later on the target device)
`-aio`	Download and optimize all the AI models in a single step (this can take a while)

Download and optimize a single AI model

With the -ais X option, replace "X" with an integer number according to the sl::AI_MODELS enum:

0 - MULTI_CLASS_DETECTION: related to sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_FAST
1 - MULTI_CLASS_MEDIUM_DETECTION: related to sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_MEDIUM
2 - MULTI_CLASS_ACCURATE_DETECTION: related to sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_ACCURATE
3 - HUMAN_BODY_FAST_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_FAST
4 - HUMAN_BODY_MEDIUM_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_MEDIUM
5 - HUMAN_BODY_ACCURATE_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE
6 - HUMAN_BODY_38_FAST_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_FAST with sl::BODY_FORMAT::BODY_38
7 - HUMAN_BODY_38_MEDIUM_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_MEDIUM with sl::BODY_FORMAT::BODY_38
8 - HUMAN_BODY_38_ACCURATE_DETECTION: related to sl::BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE with sl::BODY_FORMAT::BODY_38
9 - PERSON_HEAD_DETECTION: related to sl::OBJECT_DETECTION_MODEL::PERSON_HEAD_BOX_FAST
10 - PERSON_HEAD_ACCURATE_DETECTION: related to sl::OBJECT_DETECTION_MODEL::PERSON_HEAD_BOX_ACCURATE
11 - REID_ASSOCIATION: related to sl::BatchParameters::enable
12 - NEURAL_LIGHT_DEPTH: related to sl::DEPTH_MODE::NEURAL_LIGHT
13 - NEURAL_DEPTH: related to sl::DEPTH_MODE::NEURAL
14 - NEURAL_PLUS_DEPTH: related to sl::DEPTH_MODE::NEURAL_PLUS

Note: the numeric IDs follow the order of the sl::AI_MODELS enum and can change between major ZED SDK versions. Always verify the list matching your installed ZED SDK version by running the tool with the -h flag.

For more information about all the available ZED Diagnostics commands, use the -h flag or refer to the ZED Diagnostics documentation.