Revision history [back]

Here are the steps to install mmcv-full in a SageMaker inference endpoint:

1. Create a new SageMaker notebook instance or use an existing one.
2. Open a Jupyter notebook and create a new terminal.
3. Use the following command to install mmcv-full:

!pip install mmcv-full

1. Once the installation is complete, create a new SageMaker endpoint.
2. In the SageMaker endpoint configuration, choose the instance type as ml.g4dn.xlarge or a higher instance type, as mmcv-full requires a GPU instance.
3. In the "Advanced configuration" section of the endpoint configuration, add the following code to the "Start notebook and/or run a script" field:

import subprocess

def install(package):
    subprocess.check_call([sys.executable, "-m", "pip", "install", package])

install('mmcv-full')

1. Save and deploy the SageMaker endpoint.
2. You can now use mmcv-full in the inference code of your endpoint.