First, after installing the 'Hailo AI Software Suite' with Hailo AI Software Suite Installation, you will find a TAPPAS folder in the /artifacts directory. But if you want to install TAPPAS isolated, you must need to follow this wiki.
TAPPAS Installation
Here are the steps to install TAPPAS:
1. Download TAPPAS
First, download the file tappas_VERSION_linux_installer.zip from the Hailo Developer Zone, as shown in the image below:
2. Unzip TAPPAS file
Next, move the .zip file to the folder where the Hailo AI Software Suite is located. Then, unzip the downloaded file using the following command:
unzip tappas_VERSION_linux_installer.zip
3. Install the dependencies
After unzipping the file, you need to install the required dependencies with the following commands:
sudo apt-get install -y rsync ffmpeg x11-utils python3-dev python3-pip python3-setuptools python3-virtualenv python-gi-dev libgirepository1.0-dev gcc-12 g++-12 cmake git libzmq3-dev
sudo apt-get install -y libopencv-dev python3-opencv
sudo apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-bad1.0-dev gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio
sudo apt install python3-gi python3-gi-cairo gir1.2-gtk-3.0
sudo apt-get install libcairo2-dev
2. Install TAPPAS
First, activate your virtual environment using the following command:
source hailo_ai_sw_suite/hailo_venv/bin/activate
Next, define the TAPPAS_WORKSPACE by running the following command:
export TAPPAS_WORKSPACE=[directory]/hailo_ai_sw_suite/artifacts/tappas/
- Note:
- Replace [directory] with the path to the directory where the hailo_ai_sw_suite directory is located.
Then, execute the following command:
./install.sh --skip-hailort
- Note:
- The install.sh script is located in the TAPPAS[version] folder.
Run TAPPAS examples
TAPPAS examples
TAPPAS includes several examples. To access them, navigate to the following path:
$TAPPAS_WORKSPACE/hailo_ai_sw_suite/artifacts/tappas/apps/h8/gstreamer/general
In this directory, you will find the following examples:
cascading_networks depth_estimation face_recognition license_plate_recognition multistream_detection python sanity_pipeline century detection instance_segmentation multi_person_multi_camera_tracking multistream_multidevice README.rst tiling
When accessing each example, a .sh file with the same name as the folder will be found. The following demonstrates how to execute the 'detection' example.
First, navigate to the detection folder by running:
cd detection
Then, execute the example with the following command:
./detection.sh
This script will execute a GStreamer pipeline that plays a video and displays the predictions made by the model as shown bellow:
