ML Solution for unstructured data containing Images and videos

aswinkks — Tue, 25 Mar 2025 12:47:58 GMT

Hi,

I have a use case of developing an entire ML solution within Databricks starting from ingestion to inference and monitoring, but the problem is that we have unstructured data containing Images and Video for training the model using frameworks such as Computer Vision, Pytorch etc. and I'm not able to find any articles or videos about how to achieve this for unstructured data, especially for Video type of data. If anyone can tell me how it can be achieved, it would be really helpful

Re: ML Solution for unstructured data containing Images and videos

stbjelcevic — Tue, 28 Oct 2025 15:25:25 GMT

Hi @aswinkks ,

This is a very broad question, but generally, when dealing with video data, you convert the videos to images and have a system in place for training and another for inference.

This Databricks blog posts explains how to set up a video classification system, and specifically calls out the step of preprocessing the videos to convert them to images: https://www.databricks.com/blog/2018/09/13/identify-suspicious-behavior-in-video-with-databricks-runtime-for-machine-learning.html

This documentation gives some explanations on setting up an image inference application: https://docs.databricks.com/aws/en/machine-learning/reference-solutions/images-etl-inference

Hopefully, those can get you started in the direction you are looking for! Please let me know if you have specific follow ups.

topic ML Solution for unstructured data containing Images and videos in Machine Learning

ML Solution for unstructured data containing Images and videos

Re: ML Solution for unstructured data containing Images and videos