How to Build a Custom YOLOv4 Object Detector using TensorFlow (License Plate Detector)
Learn how to implement and build your own Custom YOLOv4 Object Detector with TensorFlow 2.0, TensorFlow Lite, and TensorFlow TensorRT Models. Perform custom YOLOv4 object detections on images, video and webcam with high accuracy and speed. In this tutorial I will be running a custom object detector trained to detect license plates on cars!
This video will walk-through the steps of converting your custom YOLO Darknet style weights into saved TensorFlow models, and running these models. Take advantage of YOLOv4 as a TensorFlow Lite model, it's small lightweight size makes it perfect for mobile and edge devices such as a raspberry pi. Looking to harness the full powers of a GPU? Then run YOLOv4 with TensorFlow TensorRT to increase performance by up to 8x times.
GET THE CODE HERE:
DOWNLOAD MY LICENSE PLATE WEIGHTS FILE:
In this video I cover:
1. Cloning the code for tutorial
2. Downloading and Converting custom YOLOv4 weights into a saved TensorFlow model
3. Performing Custom YOLOv4 Object Detections with TensorFlow on images, video and webcam
-----------------------Resources------------------------
Train Your Own YOLOv4 Custom Object Detector in the Cloud:
Running Pre-trained YOLOv4 model with TensorFlow, TFLite, TensorRT:
The Official YOLOv4 paper:
If you enjoyed the video, toss it a like!
To Subscribe:
Thanks so much for watching!
- The AI Guy
