Snippets, your gateway to deep neural network architectures
Many of the most powerful neural networks when building deep learning models are incredibly large — making them difficult and at times daunting to start to work with. This is why we’ve pre-built many of the most commonly used neural networks on the platform — called snippets — to help you get started building your deep learning models. Using snippets makes it easier to use these large networks, without actually having to build them yourself. Let’s see how snippets can be used!
The snippets can be found in the Modeling view on the Peltarion Platform, under the section Blocks > Snippets. Using snippets allows you to save a lot of time by removing the need of having to build these models yourself and consequently, the need to double-check that you haven’t missed a block or connection during your building process. Instead, you can spend more time exploring and experimenting with the different architectures for your specific application.
The currently available snippets on the platform include popular implementations of ResNetv2, DenseNet, Inception, VGG, Tiramisu, U-Net.
Choosing the right snippet
With so many different network architectures out there, it can be confusing to figure out which one to use for your problem at hand. To start pointing you in the right direction, we’ve put together this handy table for you:
This is a good start, but how do you choose between the different network alternatives? The best way to do this is by trying all of them and see which one performs the best for your specific problem.
Want to find out more about which snippet is best suitable for your problem type and input data? Head to our Knowledge Center to find out more about all the different snippets!
Originally published at peltarion.com.
