Conversion Options

This section describes the following conversion options specific to neural network models:

• Image Inputs: Work with images as inputs for better performance and more convenience.
• Classifiers: Make classifier models with embedded class labels for the Vision framework.
• Flexible Input Shapes: Convert models that have flexible input shapes, which are common in fully convolutional models or dynamic seq2seq models.
• Composite Operators: Create operators that build on other basic operators.
• Custom Operators: Create custom implementations of operators in Swift.