Blocks
A block is the basic building unit in the Peltarion Platform. They represent the basic components of a neural network and/or the actions that can be carried out on them.
You’ll find descriptions of all blocks available in the navbar.
Pretrained blocks
Many of the most powerful neural networks have very large architectures (e.g., the Resnet 152 network has, you guessed it, 152 layers in total) which can make them tedious to build and daunting to start working with.
To help you get started, we’ve made many popular networks available as Pretrained blocks on the Peltarion Platform.
Using Pretrained blocks can save you 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 build process. Instead, you can spend more time exploring and experimenting with the different architectures for your specific application.
Pretrained blocks have already learned the basic representations from the dataset it has been trained on and can be trained on a small domain-specific dataset to provide value.
Examples of pretrained blocks available are:
-
EfficientNet, used image classification and similarity
-
Multilingual BERT, used for text classification and regression
-
Universal sentence encoder, used for text similarity.