Try a service remotely

1. Choose your module and deploy

The first step is to choose a module from the Dashboard. There you will be able to find all the modules ready to be used under the tag Inference.

For educational purposes we are going to use a general model to identify images. This will allow us to see the general workflow. Select that module and follow the instructions to deploy it, making sure to select DEEPaaS as the Service in the configuration.

2. Accessing the module and make predictions

Go to the Deployments tab and select the deepaas endpoint in your newly deployed module. It will open the Swagger UI with the API documentation, where you can test the module’s functionality, as well as perform other actions.

../../_images/deepaas.png

Go to the predict() function and upload the file/data you want to predict (in the case of the image classifier this should be an image file). The appropriate data formats of the files you have to upload are often discussed in the module’s Marketplace page.

The response from the predict() function will vary from module to module but usually consists on a JSON dict with the predictions. For example the image classifier return a list of predicted classes along with predicted accuracy. Other modules might return files instead of a JSON.

Tip

If you run into problems you can always check the Frequently Asked Questions (FAQ).