First steps with DepthAI

Hello DepthAI users!

In this guide, I assume you just got your OAK camera (e.g. OAK-D) and you want to give it the first try to explore what is possible with it and what you can achieve when working with it.

  • First, we will run a DepthAI demo script, that will allow you to preview DepthAI functionalities.

  • Following up, I will go through some of the options available in the demo script and show their usage/results

  • Last, you will receive useful links to expand your knowledge further and check open-sourced use-case implementations, code examples, and tutorials, that you can use as a starting point for your projects.

Let’s start with the device setup below

Connect the OAK camera (USB)

If your OAK came with an included USB cable, we suggest using that to connect the OAK camera to the host computer.


Make sure to use USB3 cable! If you aren’t, force USB2 communication in the program.


USB3 cable is colored blue in the inside of the USB-A connector of the USB-C cable.

Make sure that the device is connected to your host (which can be a PC or Raspberry Pi or another capable device) directly to a USB port, or via a powered USB hub.

On Ubuntu, you can check if a new USB device was detected by running

$ lsusb | grep MyriadX
Bus 003 Device 002: ID 03e7:2485 Intel Movidius MyriadX


If you are running other OS than Ubuntu, or you think something has gone wrong, we have detailed OS-specific installation guides here.

Connect the OAK camera (PoE)

If you are using PoE device, you should follow the Getting started with OAK PoE devices tutorial.

Use Windows Installer

If you prefer, we’ve encapsulated all setup procedures inside a single .exe file you can download here and skip the Setup section.

When downloaded and run, it will install all necessary components and package requirements. Once finished, it will run the demo script automatically


In this section, I will describe how to install the demo script manually with a command line

Download demo script

To download the demo script, you can either use git or directly download a zip file

From zip file

First, download a repository package from here and then unpack the archive to a directory of preference. Next, open a terminal session in this directory.

From git

First, open the terminal session and go to a directory of preference, where you’d like to download your demo script. Then, run the following code to download the demo script

$ git clone

After the repository is downloaded, make sure to enter the downloaded repository by running

$ cd depthai

Create python virtualenv (optional)

To create and use the virtualenv, you can follow an official python guide to virtualenvs or follow os-specific guides on the web, like “How to Create Python 3 Virtual Environment on Ubuntu 20.04”

This will make sure that you are using a fresh environment and that Python 3 is the default interpreter - this can help to prevent potential issues.

I usually create and use virtualenvs by running

$ python3 -m venv myvenv
$ source myvenv/bin/activate
$ pip install -U pip

And this may require installing these packages prior

$ apt-get install python3-pip python3-venv

Install requirements

Once the demo source code is downloaded, and you have your terminal session set up, the next thing that has to be done is to install all additional packages that this script requires (together with the depthai Python API itself).

To install these packages, run the script

$ python3


If you are using a Linux system, in most cases you have to add a new udev rule for our script to be able to access the device correctly. You can add and apply new rules by running

$ echo 'SUBSYSTEM=="usb", ATTRS{idVendor}=="03e7", MODE="0666"' | sudo tee /etc/udev/rules.d/80-movidius.rules
$ sudo udevadm control --reload-rules && sudo udevadm trigger

Now, you should be able to start using the demo script, which we will do now

Run demo script

Having everything set up, we are now ready to use the demo script by running

$ python3

Default run

Running the demo for the first time, the script will compile and download a default mobilenet-ssd model, configure the OAK camera and then show a default color preview that will contain a scaled preview from the RGB camera from your device.

Default run

Change preview

To see other previews from the device, you can use the preview switcher that is visible in the top-left section of the GUI

preview selector location
Available previews





Shows preview from color camera


Shows preview from right mono camera

Disabled if no AI model is running


Shows preview from left mono camera

OAK-D needed


Shows preview from right mono camera

OAK-D needed


Shows disparity map calculated from depthRaw preview and JET colored. Best for visualizing depth

OAK-D needed


Shows raw depth map. Best for depth-based calculations

OAK-D needed


Shows disparity map produced on device

OAK-D needed


Shows disparity map produced on device and JET colored. Should be the same as depth preview but produced on the device.

OAK-D needed


Rectified left camera frames

OAK-D needed


Rectified right camera frames

OAK-D needed

Default model

While the demo was running, you could see the detection results - and if you were standing in front of the camera, you should see yourself detected as a person with a pretty high probability.

The model that is used by default is a MobileNetv2 SSD object detector trained on the PASCAL 2007 VOC classes, which are:

  • Person: person

  • Animal: bird, cat, cow, dog, horse, sheep

  • Vehicle: airplane, bicycle, boat, bus, car, motorbike, train

  • Indoor: bottle, chair, dining table, potted plant, sofa, TV/monitor

So give it a try to detect different objects, like bottles or apples

bottles and apples

Or even cats


Using other models

We have prepared other models, which you can try and evaluate with ease. To run the demo script with e.g. face-detection-retail-0004, click on the CNN Model combo box and select mentioned model

cnn model location

Which will allow you to detect human faces, like below


You can use this combo box to change the model that is being run on the DepthAI. It’s also possible to use command line to select

$ python3 -cnn face-detection-retail-0004

Below, there is a list of models that you can use, having just the demo script downloaded

Available models






People segmentation




Face detection




Face detection




Object detection (20 classes)




People detection




People detection




People, vehicle and bike detection




Object detection (80 classes)




Object detection (80 classes)




Vehicle detection




License plate detection




Pose estimation (openpose)




Pose estimation (intel)



  • deeplabv3p_person - Allows to highlight parts of the image where a person is detected

    $ python3 -cnn deeplabv3p_person
  • face-detection-adas-0001 - Allows to detect faces on the image (slower)

    $ python3 -cnn face-detection-adas-0001
  • face-detection-retail-0004 - Allows to detect faces on the image (faster)

    $ python3 -cnn face-detection-retail-0004
  • mobilenet-ssd - Object detector that detects 20 different classes (default)

    $ python3 -cnn mobilenet-ssd
  • pedestrian-detection-adas-0002 - allows to detect people on the image (slower)

    $ python3 -cnn pedestrian-detection-adas-0002
  • person-detection-retail-0013 - allows to detect people on the image (faster)

    $ python3 -cnn person-detection-retail-0013
  • person-vehicle-bike-detection-crossroad-1016 - allows to detect both people, bikes and vehicles on the image

    $ python3 -cnn person-vehicle-bike-detection-crossroad-1016
  • yolo-v3 - Object detector that detects 80 different classes (slower)

    $ python3 -cnn yolo-v3
  • tiny-yolo-v3 - Object detector that detects 80 different classes (faster)

    $ python3 -cnn tiny-yolo-v3
  • vehicle-detection-adas-0002 - allows to detect vehicles on the image

    $ python3 -cnn vehicle-detection-adas-0002
  • vehicle-license-plate-detection-barrier-0106 - allows to detect both vehicle and license plate on the image (only Chinese license plates)

    $ python3 -cnn vehicle-license-plate-detection-barrier-0106
  • openpose2 - Human pose estimation model

    $ python3 -cnn openpose2
  • human-pose-estimation-0001 - Human pose estimation model from Open Model Zoo

    $ python3 -cnn human-pose-estimation-0001

All of the data we use to download and compile a model can be found here.

Demo usage

In this section, we’ll go through the config options available in the demo script, allowing you to try out different configurations

Config options

AI Properties

AI config


  • Enabled: Turns AI on/off. Turning it off will prevent any neural network from being run, which will also save some of the memory. Useful for situations where we’re more focused on Depth/Encoding rather than AI processing

Basic properties:

  • CNN Model: Choose which model to run on DepthAI, see more at Using other models

  • SHAVEs: Determines the number of SHAVE cores used to compile the neural network. The higher the value, the faster network can run, but this also limits features that can be enabled at once.

  • Model source: Specify which camera preview will be taken as model input, so which frames will be sent to a neural network to perform inference

  • Full FOV: If enabled, it will scale down the camera image to meet the nn input size. If disabled, before scaling, it will crop the image to meet the NN aspect ratio


  • OpenVINO version: Specify the OpenVINO version that will be used to compile the MyriadX blob and run the pipeline. It’s recommended to use the latest version for most cases

  • Label to count: Allows to display a count of a specific label visible in the demo (e.g. if you want to count the number of cats in the preview with the default model, you can do so by selecting cat as a count label and restarting the script)

  • Spatial bounding box: When enabled, will draw a bounding box on depth previews that show which part of the detection area was taken into depth estimation.

  • SBB Scale Factor: Determines the size of the spatial bounding box in comparison to the detection bounding box.

Depth Properties

Depth config


  • Enabled: Turns Depth on/off. Turning it off will prevent the stereo node from being created, which will also save some of the memory. Useful for situations where we’re more focused on AI processing/Encoding rather than depth.

  • Use Disparity: If not set (default), the demo script will calculate the disparity map on host, based on the depth map. If enabled, the same processing will be performed on the device, consuming some of the memory but limiting host resource usage.

Basic properties:

  • Median Filtering: Specifies the type of noise removing median filter applied to the depth map

  • Subpixel: Enables subpixel mode, which improves the depth precision and is especially useful for long-range measurements

  • Left Right Check: Enables left-right check, that is used to remove incorrectly calculated disparity pixels due to occlusions at object borders

  • Extended Disparity: Enables extended disparity mode, that allows a closer minimum distance for the given baseline

  • Depth Range: Specifies the minimum and maximum distance calculated by the device

  • LRC Threshold: Specifies the max difference between disparity pixels that will make the pixel invalidated (the higher threshold, the more points will get through)

Camera Properties

Camera config

Basic properties:

  • FPS: Specifies how fast should the camera capture the frames

  • Resolution: Specifies camera sensor resolution and thus captured frame size


  • ISO: Controls the light gathering ability of the camera

  • Exposure: Controls the exposure time of the camera

  • Saturation: Controls the intensity of colors in a frame

  • Contrast: Controls the visual ratio of different tones in a frame

  • Brightness: Controls how dark or light the colors are in a frame

  • Sharpness: Controls the clarity of details in a frame




  • Switches: enable recording of specified camera

  • FPS inputs: specifies recording FPS (default 30)

  • Destination: specifies a directory path where the recordings will be stored


  • Switches: enable logging of the specified feature

  • Destination: specifies a file path where the report file will be stored

Using custom models


Using custom models requires a locally downloaded version of the depthai repository. If you’ve been using installer to download and run the script, adding custom models won’t work. Please follow Setup section on how to download and set up the repository.

Let’s assume you want to run a custom model which you downloaded from the model zoo or trained yourself (or both). To prepare your model to be runnable on DepthAI, it has to be compiled into MyriadX blob format - which is an optimized version of your model, capable of utilizing MyriadX chip as a processing unit.

In our demo script, we support a few ways you can run your custom blob, which will be covered below. As an example, I’ll add a custom face detection network called custom_model (substitute with your preferred name) and run it with the demo script

Compile MyriadX blob

To receive a MyriadX blob, the network has to be already in OpenVINO IR format (consisting of .xml and .bin files) that will be used for compilation. We won’t focus here on how to obtain this representation for your model, but be sure to check official OpenVINO conversion guide.

To convert custom_model.xml and custom_model.bin, we’ll use the blobconverter cli - our tool that utilizes Online MyriadX blob converter to perform the conversion. No local OpenVINO installation is needed in this case, as all of the dependencies are already installed on the server. If your model is in TensorFlow or Caffe format, you can still use our tool for conversion, just note that you’ll have to use different input flags and sometimes provide a custom model optimizer args (Read more)

First, let’s install blobconverter from PyPi

$ python3 -m pip install -U blobconverter

Now, having the blobconverter installed, we can compile our IR files with the following command

$ python3 -m blobconverter --openvino-xml /path/to/custom_model.xml --openvino-bin /path/to/custom_model.bin

By running this command, blobconverter sends a request to the BlobConverter API to perform a model compilation on provided files. After compilation, the API responds with a .blob file and deletes all source files that were sent with the request.

After a successful compilation, blobconverter returns the path to the downloaded blob file. Since this blob is required by the depthai repository, let’s move it there

$ mkdir <depthai_repo>/resources/nn/custom_model
$ mv <path_to_blob> <depthai_repo>/resources/nn/custom_model


We need to provide some additional configuration for the demo script to run this blob. The demo script will look for a custom_model.json for details on how to configure the pipeline and parse the results.

If your model is based on MobileNetSSD or Yolo, you can use our detection output format. If it’s a different type of network, you can use raw (default) output format and provide a custom handler file to decode and display the NN results.

You can use these configuration examples to customize your custom_model.json inside resources/nn/custom_model directory

  • MobileNetSSD (we will use this config)

        "output_format" : "detection",
        "NN_family" : "mobilenet",
        "confidence_threshold" : 0.5,
        "input_size": "300x300"
  • Yolo

        "output_format" : "detection",
        "NN_family" : "YOLO",
        "input_size": "416x416",
        "NN_specific_metadata" :
            "classes" : 80,
            "coordinates" : 4,
            "anchors" : [10,14, 23,27, 37,58, 81,82, 135,169, 344,319],
            "anchor_masks" :
                "side26" : [1,2,3],
                "side13" : [3,4,5]
            "iou_threshold" : 0.5,
            "confidence_threshold" : 0.5
    "nn_config": {
        "output_format" : "raw",
        "input_size": "300x300"
    "handler": ""

Run the demo script

Having the files in place, we can now run the demo with our custom model

custom model location

And you should see the output and your NN results displayed (or printed in the console if raw was selected and there is no handler file)

custom model

Be sure to check the advanced sections below or see Next steps

Custom handler

Custom handler is a file that the demo script will load and execute to parse the NN results. We specify this file with handler config value, specifying a path to the file of preference. It also requires raw output format, since it prevents the script from handling the results itself.

The file should contain two methods - decode(nn_manager, packet) and draw(nn_manager, data, frames)

def decode(nn_manager, packet):

def draw(nn_manager, data, frames):

The first method, decode, is called whenever a NN packet arrives from the pipeline (stored as a packet param) also providing a nn_manager object that contains all nn-related info that was used by the script (like input size etc.). The goal of this function is to decode the received packets from the NN blob into meaningful results that can later be displayed.

Second one, draw, is called with the NN results (returned from decode), nn_manager object and frames array, having [(<frame_name>, <frame>), (<frame_name>, <frame>), ...] items. This array will contain frames that were specified with the -s/--show param. The goal of this function is to draw the decoded results onto received frames.

Below, you can find an example file that decodes and displays MobilenetSSD-based results.

import cv2
import numpy as np
from depthai_helpers.utils import frame_norm

def decode(nn_manager, packet):
    bboxes = np.array(packet.getFirstLayerFp16())
    bboxes = bboxes.reshape((bboxes.size // 7, 7))
    bboxes = bboxes[bboxes[:, 2] > 0.5]
    labels = bboxes[:, 1].astype(int)
    confidences = bboxes[:, 2]
    bboxes = bboxes[:, 3:7]
    return {
        "labels": labels,
        "confidences": confidences,
        "bboxes": bboxes

decoded = ["unknown", "face"]

def draw(nn_manager, data, frames):
    for name, frame in frames:
        if name == nn_manager.source:
            for label, conf, raw_bbox in zip(*data.values()):
                bbox = frame_norm(frame, raw_bbox)
                cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), (255, 0, 0), 2)
                cv2.putText(frame, decoded[label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
                cv2.putText(frame, f"{int(conf * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)

With the custom face detection model, using this code we receive the following output

custom model custom handler

We already use this handler mechanism to decode deeplabv3p_person, that comes as one of the available networks in the demo script to use

On-demand compilation

Since files in the IR format can be large, and we’re both downloading the blob and uploading IR format to the server, we have incorporated an OpenVINO-like model.yml file structure that the BlobConverter server uses internally as well. You can check how this file looks like in OpenVINO model zoo or in available models in demo script.

This file is used by the OpenVINO model downloader that is used to download the required files for compilation. In our demo script, we use these files to provide a URL to the NN source files instead of uploading them along with the source code. It is also useful because on-demand compilation allows us to use the same configuration while requesting a different amount of MyriadX SHAVE cores.

To download the blob using model.yml file, run

$ python3 -m blobconverter --raw-config /path/to/model.yml --raw-name custom_model

You can also leave the model.yml file inside the resources/nn/<name> directory. This will make the demo script perform the conversion for you and run the received blob

$ python3 -cnn <name>

Customize the demo code

Callbacks file

If you’d like to add some custom functionalities to the demo yourself or just check how do certain variables look like, you can use a callbacks file, that should contain methods that the demo will call during execution on specific events.

An example of a callbacks file that is available in the repo is below

def shouldRun():
  pass  # Called to determine if the demo should be running

def onNewFrame(frame, source):
  pass  # Called when a new frame is available

def onShowFrame(frame, source):
    pass  # Called when a frame is about to be displayed

def onNn(nn_packet):
    pass  # Called when a new NN packet is available

def onReport(report):
    pass  # Called when a new report is available

def onSetup(*args, **kwargs):
    pass  # Called when the demo script is setting up

def onTeardown(*args, **kwargs):
    pass  # Called when the demo script is finishing

def onIter(*args, **kwargs):
    pass  # Called on each demo script iteration (internal loop)

These methods allow building custom functionalities on top of the demo script itself, whether it’s just printing or counting the data from NN or modifying how to display the frames or even make custom database/API connections to send the data to external destination.

By default, the demo script will use file in the repository, but this path can be changed using -cb <path> / --callback <path> flags

Importing demo as a class

If preferred, the Demo script can also be imported like a regular class - this allows to control when the demo is starting up and when does it run. A simple example of how to run the demo from Python code is shown below

from depthai_demo import Demo
from depthai_helpers.arg_manager import parseArgs
from depthai_helpers.config_manager import ConfigManager

args = parseArgs()
conf = ConfigManager(args)
demo = Demo(onNewFrame=<fn>, onShowFrame=<fn>, onNn=<fn>, onReport=<fn>, onSetup=<fn>, onTeardown=<fn>, onIter=<fn>) # all params are optional

Remember that PYTHONPATH env variable must contain a path do depthai repository for the imports to work. Alternatively, you can place the script along in the repository

Next steps

In the previous sections, we learned how to preview basic DepthAI features. From this point, you can explore the DepthAI world further

  • Looking for inspiration?

    Check our Example Use Cases for ready to use applications that solve a specific problem on DepthAI

  • Want to start coding?

    Be sure to check hello world tutorial on API section for a step-by-step introduction to the API

  • Want to train and deploy a custom model to DepthAI?

    Visit Custom training page for ready to use Colab notebooks

Got questions?

We’re always happy to help with development or other questions you might have.