Extracting the inference results
In the previous section, you let your scheduler run thrice. The results from any successful inference will be stored in the output location on S3 that you configured at the beginning of this chapter. Let's download one of these files and look at its content:
- Log in to your AWS console.
- At the top left of your console, you will see a Services drop-down menu that will display all the available AWS services. In the Storage section, look for the S3 service and click on its name to go to the S3 console.
- Navigate to your bucket and then to
inference-data
and finally tooutput
. Each inference execution creates a new directory named after the timestamp at which the scheduler woke up.
- In this directory, you will find a single file named
results.jsonl
. This is a JSON-line file. Click the checkbox next to its name and click on the Download button.
...