nvidia/vista-3d

Pull and run nvidia/vista-3d using Docker (this will download the full model and run it in your local environment)

Get API KeyCopy Code
$ docker login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

Start NIM

1. Export NGC_API_KEY variable.

Copy Code
export NGC_API_KEY=<your personal NGC key>

2. The NIM container automatically downloads any required models. To save time and bandwidth it is recommended to provide a local cache directory. This way the NIM will be able to reuse any already downloaded models. Execute the following command to setup the cache directory:

Copy Code
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p $LOCAL_NIM_CACHE

Note that you may need to run (sudo) chmod -R 777 $LOCAL_NIM_CACHE after the VISTA-3D model is downloaded to avoid permission issues.

3. Run the NIM container with the following commands:

Copy Code
docker run --rm -it --name vista3d \
   --runtime=nvidia -e CUDA_VISIBLE_DEVICES=0 \
   --shm-size=8G \
   -p 8000:8000 \
   -e NGC_API_KEY=$NGC_API_KEY \
   nvcr.io/nim/nvidia/vista3d:latest

This command will start the NIM container and expose port 8000 for the user to interact with the NIM.

4. Open a new terminal, leaving the terminal open with the just launched service. In the new terminal, wait until the health check end point returns {"status":"ready"} before proceeding. This may take a couple of minutes. You can use the following command to query the health check.

Copy Code
curl -X 'GET' \
    'http://localhost:8000/v1/health/ready' \
    -H 'accept: application/json'

Python Client Example: Segment Everything

1. Save following Python example to a file named nim_client.py.

Copy Code
import requests
import zipfile

base_url = "http://localhost:8000"

data = {
    "image": "https://assets.ngc.nvidia.com/products/api-catalog/vista3d/example-1.nii.gz",
}

def unzip_file(zip_filepath, dest_dir):
    with zipfile.ZipFile(zip_filepath, 'r') as zip_ref:
        zip_ref.extractall(dest_dir)

response = requests.post(f"{base_url}/v1/vista3d/inference", json=data)
if response.status_code == 200:
    output_folder = "output"
    output_zip_name = "output.zip"

    with open(output_zip_name, "wb") as f:
        f.write(response.content)

    unzip_file(output_zip_name, output_folder)

2. Execute the example.

Copy Code
python nim_client.py

3. The resulting segmentation file will be returned and written to output.zip.

Copy Code
cat output.zip

Shell Client Example

1. Save the following Shell example to a file named nim_client.sh.

Copy Code
LOCAL_URL='http://localhost:8000/v1/vista3d/inference'
DATA=$(cat <<EOF
{
    "image": "https://assets.ngc.nvidia.com/products/api-catalog/vista3d/example-1.nii.gz"
}
EOF
)
response=$(curl -s -o output.zip  -w "%{http_code}" -X POST -H "Content-Type: application/json" -d "$DATA" $LOCAL_URL)
if [ "$response" -eq 200 ]; then
  echo "Response Success, save inference results into folder: output"
  unzip -o "output.zip" -d "output"
else
  echo "Request failed with status $response"
fi

2. Execute the example.

Copy Code
chmod +x nim_client.sh

./nim_client.sh

3. Results will be returned in ZIP format. You will be able to see the label formatted output; you can also use curl to save the output directly to file.