Getting Started
Please follow instructions in Clara installation to install the docker image.
Additionally, you need to create and mount a folder for the AIAA server to save all the models, logs and configurations.
mkdir aiaa_experiments
The system requirements of AIAA depend on how many models you want to load in the server. If your models are big and you don’t have enough system RAM/GPU memory, please load one model at a time.
AIAA supports the following 2 modes.
NATIVE (PyTorch)
start_aiaa.sh -w aiaa_experiments --engine AIAA
TRITON
To run AIAA with the Triton backend, we need to run two containers. We recommend using docker-compose to start AIAA.
Please follow docker-compose installation guide to install docker-compose. And also check docker GPU support prerequisites
You can install docker-compose using pip. For example: pip install docker-compose
docker-compose version needs to be >= 1.28.5. Use docker-compose version to check.
Create a file called docker-compose.yml and paste the following contents:
version: "3.8"
services:
clara-train-sdk:
image: ${CLARA_IMAGE}
command: >
sh -c "mkdir -p /workspace/logs /workspace/triton &&
start_aiaa.sh \
--workspace /workspace \
--port ${AIAA_PORT} \
--engine TRITON \
--triton_ip tritonserver \
--triton_port 8000 \
--triton_proto http \
--triton_model_path /workspace/triton \
--triton_verbose 0 2>&1 | tee /workspace/logs/container.aiaa.log"
ports:
- "${AIAA_PORT}:5000"
volumes:
- ${AIAA_WORKSPACE}:/workspace
networks:
- aiaa
shm_size: 1gb
ulimits:
memlock: -1
stack: 67108864
depends_on:
- tritonserver
logging:
driver: json-file
tritonserver:
image: ${TRITION_IMAGE}
command: >
sh -c "mkdir -p /workspace/logs /workspace/triton &&
tritonserver \
--model-store=/workspace/triton \
--model-control-mode=poll \
--repository-poll-secs=5 \
--log-verbose=0 2>&1 | tee /workspace/logs/container.triton.log"
volumes:
- ${AIAA_WORKSPACE}:/workspace
networks:
- aiaa
shm_size: 1gb
ulimits:
memlock: -1
stack: 67108864
restart: unless-stopped
logging:
driver: json-file
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: [ '0' ]
capabilities: [ gpu ]
networks:
aiaa:
Create a file called docker-compose.env and paste the following contents:
CLARA_IMAGE=nvcr.io/nvidia/clara-train:4.1
TRITION_IMAGE=nvcr.io/nvidia/tritonserver:21.10-pyt-python-py3
# Basic AIAA settings
AIAA_PORT=5000
AIAA_WORKSPACE=/share/aiaa_workspace # Local Path (fix/update this)
Please modify the <YOUR WORKSPACE> to the absolute path on your system where you want to use it as AIAA workspace (the folder you created in this step.)
Then we can use the following command to run:
docker-compose --env-file docker-compose.env -p aiaa_triton up --remove-orphans -d
And this is the command to stop:
docker-compose --env-file docker-compose.env -p aiaa_triton down --remove-orphans
To check the log you can do:
docker-compose --env-file docker-compose.env -p aiaa_triton logs -f -t
Application logs are redirected to **workspace/logs/container.xxx.log**
To start only one service you can do
docker-compose --env-file docker-compose.env -p aiaa_triton up [the service name]
You can type docker ps to check if AIAA and Triton is running.
You can modify the “AIAA_PORT” to the port you want to use on the host machine.
You can modify the “device_ids” section under “deploy” section of “tritonserver” service to change the GPU id that you want to use.
Following are the options available while starting the AI-Assisted Annotation Server.
Option |
Default Value |
Example |
Description |
|---|---|---|---|
BASIC |
|||
workspace |
Workspace Location for AIAA Server to save all the configurations, logs and models. It is required while starting AIAA |
||
debug |
|
Enable Debug level Logging for AIAA Server logs |
|
Native/Triton |
|||
engine |
AIAA |
|
The inference engine of AIAA server. Choose from AIAA or Triton. AIAA means to directly use the framework to do inference. |
triton_ip |
localhost |
|
Triton server ip |
triton_port |
8000 |
|
Triton server service port based on the triton_proto |
triton_proto |
http |
Protocol to communicate with Triton server. (http or grpc) |
|
triton_shmem |
no |
|
Whether to use shared memory communication between AIAA and Triton (no, system, or cuda) |
triton_model_path |
<workspace dir>/triton |
Triton models path |
|
triton_verbose |
0 |
Set Triton verbose logging level. Zero (0) disables verbose logging and values >= 1 enables verbose logging. |
Native mode means that AIAA uses PyTorch to run the inference directly.
Workspace
AIAA Server uses the workspace directory for creating and managing MONAI Label app.
For more details on MONAI Label app, please refer: https://docs.monai.io/projects/label/en/latest/modules.html
Following are a few files/folders explained from the workspace directory. Note that INTERNAL means that the file or
directory is managed by the AIAA server and we suggest not to change it.
File/Folder |
Description |
|---|---|
logs/ |
|
model/ |
|
triton/ |
|
lib/ |
|
We suggest you create a new folder to be the workspace so that if you want to delete these files you can just remove that workspace folder.
The workspace is actually a MONAI Label app. That means, you can use it to run MONAI Label Server directly.
For example: monailabel start_server --app workspace
Logs
Once the server is up and running, you can watch or pull the server logs in the browser.
http://127.0.0.1:$AIAA_PORT/logs (server will fetch last 100 lines from the current log file)
http://127.0.0.1:$AIAA_PORT/logs?lines=-1 to fetch everything from the current log file.
All the URLs with 0.0.0.0 or 127.0.0.1 is only accessible if your browser and server are on the same machine.
The $AIAA_PORT is the port specified in “docker-compose.env”.
You can use ip a to find your server’s IP address and check it remotely on http://[server_ip]:$AIAA_PORT/logs.