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!
#yolov4 #tensorflow #objectdetection
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: https://github.com/theAIGuysCode/tens...
DOWNLOAD MY LICENSE PLATE WEIGHTS FILE: https://drive.google.com/file/d/1EUPt...
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: • YOLOv4 in the CLOUD: Build and Train ...
Running Pre-trained YOLOv4 model with TensorFlow, TFLite, TensorRT: • YOLOv4 Object Detection with TensorFl...
The Official YOLOv4 paper: https://arxiv.org/abs/2004.10934
If you enjoyed the video, toss it a like! 👍
To Subscribe: / @theaiguy
Thanks so much for watching!
The AI Guy
Watch video How to Build a Custom YOLOv4 Object Detector using TensorFlow (License Plate Detector) online without registration, duration hours minute second in high quality. This video was added by user The AI Guy 27 July 2020, don't forget to share it with your friends and acquaintances, it has been viewed on our site 46,035 once and liked it 836 people.