YOLOv5 TFLite

This guide explains how to run YOLOv5 with tflite backend.

---

(Supports CPU on every platform, Full Dynamic Support)

You can use TFLite powered detector by specifying the backend parameter.

from cvu.detector import Detector
detector = Detector(classes="coco", backend = "tflite"))

Internally, the Detector will load TFLite pretrained Yolov5s weight model.

We will update dynamic export info soon, please check back again.

Notes

• We currently use tf.lite for Interpreter creation. In next update, we'll provide option of tflite_runtime and pycoral