Using DeepStack with NVIDIA GPUs¶
DeepStack GPU Version serves requests 5 - 20 times faster than the CPU version if you have an NVIDIA GPU.
Before you install the GPU Version, you need to follow the steps below.
Step 1: Install Docker¶
If you already have docker installed, you can skip this step.
sudo apt-get update
sudo apt-get install curl
curl -fsSL get.docker.com -o get-docker.sh && sh get-docker.sh
Step 2: Setup NVIDIA Drivers¶
Install the NVIDIA Driver
Step 3: Install NVIDIA Container Toolkit¶
Run the commands below
# Add the package repositories
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
sudo systemctl restart docker
If you run into issues, you can refer to this GUIDE
Step 4: Install DeepStack GPU Version¶
sudo docker pull deepquestai/deepstack:gpu-2022.01.1
If you are running an old system without modern cpu instructions such as AVX, please use the Legacy System Version
Step 5: RUN DeepStack with GPU Access¶
Once the above steps are complete, when you run DeepStack, add the args –gpus all
sudo docker run --gpus all -e VISION-SCENE=True -v localstorage:/datastore \
-p 80:5000 deepquestai/deepstack:gpu-2022.01.1
Basic Parameters
–gpus all This enables gpu access to the DeepStack container
-e VISION-SCENE=True This enables the scene recognition API.
-v localstorage:/datastore This specifies the local volume where DeepStack will store all data.
-p 80:5000 This makes DeepStack accessible via port 80 of the machine.
Once installed, run the example scene recognition code to verify your installation is working.
RUN with All APIs¶
You can run DeepStack with all the APIs enabled. Use the command below
sudo docker run --gpus all -e VISION-SCENE=True -e VISION-DETECTION=True -e VISION-FACE=True -v localstorage:/datastore -p 80:5000 deepquestai/deepstack:gpu-2022.01.1