The Vehicle Classification library is used to classify vehicle images (vehicle make or vehicle type). Such neural networks are trained on CompCars and they can identify the objects from 163 classes or 12 classes. The Vitis AI Library integrates networks including vehicle_make_resnet18_pt and vehicle_type_resnet18_pt into AMD libraries. The input is a picture with an object and the output is the top-K most probable category.
Figure 1. Vehicle Classification Example
| No | Model Name | Framework |
|---|---|---|
| 1 | vehicle_type_resnet18_pt | PyTorch |
| 2 | vehicle_make_resnet18_pt | PyTorch |