-
Notifications
You must be signed in to change notification settings - Fork 19
YOLOv5 TensorFlow
Aditya Lohia edited this page Jun 8, 2022
·
1 revision
This guide explains how to run YOLOv5 with TensorFLow backend.
(Supports every device on every platform including TPU, Full Dynamic Support)
You can use TensorFlow powered detector by specifying the backend parameter.
from cvu.detector import Detector
detector = Detector(classes="coco", backend = "tensorflow"))Internally, the Detector will load Tensorflow SavedModel pretrained Yolov5s weight model. You can also set device='tpu' (tested on colab)
We will update dynamic export info soon, please check back again.