Instantly scale AI and machine learning workloads on GPU on-demand
Functionality Product update UbiOps
March 15, 2023 / July 26, 2023 by [email protected]
In our previous blogs on pipeline operators, we saw how we could use the pipeline operators to speed up our inference, to add unit tests to the input of our machine learning model and to conditionally routing the pipeline request to one way or the other. With UbiOps latest release, v2.22.0, we introduced a new […]
Read more »
Tagged
Functionality Technology UbiOps
January 19, 2023 / July 26, 2023 by [email protected]
Exciting things you can build with the new UbiOps operators! In our first blog on pipeline operators, we used them to speed up a video processing pipeline. Specifically, we used the create subrequests and the collect subrequests operators to analyze multiple frames of the video simultaneously, by introducing parallelization. This time we will highlight three […]
Blog Functionality UbiOps
September 8, 2021 / July 26, 2023 by [email protected]
It can be quite confusing keeping track of what all these different pipelines are and how they differ from one another. In this article, we will map out and compare a few common pipelines, as well as clarify where UbiOps pipelines fit in the general picture.
Blog Functionality
August 3, 2021 / January 5, 2024 by [email protected]
Combining R and Python in the same pipeline While hundreds of programming languages exist, Python and R remain the most popular ones to use in the world of data science. R is a great language to make visualizations and graphs, furthermore, it has many functionalities for data analysis. Python is a general-purpose language that is […]
Blog
November 26, 2020 / January 5, 2024 by [email protected]
(2020 version) In a previous article I explained how to deploy a single data science deployment onto UbiOps that could be used for object recognition. However, in the real world, it is often not that simple. In reality, you usually don’t have a single model with perfect input and output. Rather, there is a chain […]
