YOLOv3 Detection - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English

YOLOv3 is a neural network used to detect objects. The input is a 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 YOLOv3 detection.

Figure 1. YOLOv3 Detection Example

The following table lists the YOLOv3 detection models supported by the Vitis AI library.

Table 1. YOLOv3 Detection Models
No Model Name Framework
1 yolov3_voc_tf TensorFlow
2 yolov3_adas_pruned_0_9 Caffe
3 yolov3_voc
4 yolov3_bdd
5 tiny_yolov3_vmss
6 yolov3_coco_416_tf2 TensorFlow2