OFA_YOLO Detection - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English
OFA_YOLO is a neural network used to detect objects. The input is a 640x640 picture with one or more objects and the output is a vector of the result struct which is composed of the detected information. The following image shows the result of OFA_YOLO detection.
Figure 1. OFA_YOLO Detection Example

The following table lists the OFA_YOLO detection models supported by the Vitis AI Library.

Table 1. OFA_YOLO Detection Models
No Model Name Framework
1 ofa_yolo_pt PyTorch
2 ofa_yolo_pruned_0_30_pt
3 ofa_yolo_pruned_0_50_pt