- Install DSA AI Adapter by following the instructions here.
- Deploy the model using conda as explained here.
Upon completion, Fast API will be initialized, and a URL for the hosted AI models will be generated.
Developers can access the AI model location by navigating to:
Location-of-DSA-ai-adapter/aiInferenceModel/
The code is organized as follows:
- main.py: Executes the Fast API code, creating endpoints for each AI model.
- utils.py: Contains instructions for downloading and pre-loading AI models.
- ai_models folder: Houses individual code sets for pre-built AI models.
Developers can use the following code as a template for building custom segmentation models. After launching the Fast API, modifications to the code will be automatically reflected at the endpoint:
The following code serves as a template for building custom classification models: