You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
franklinOliveira 533774290c
Optimize Example YOLO post-processing speed (#16821)
2 months ago
..
README.md YOLOv8 INT8 TFLite Inference Example (#7317) 11 months ago
main.py Optimize Example YOLO post-processing speed (#16821) 2 months ago

README.md

YOLOv8 - Int8-TFLite Runtime

Welcome to the YOLOv8 Int8 TFLite Runtime for efficient and optimized object detection project. This README provides comprehensive instructions for installing and using our YOLOv8 implementation.

Installation

Ensure a smooth setup by following these steps to install necessary dependencies.

Installing Required Dependencies

Install all required dependencies with this simple command:

pip install -r requirements.txt

Installing tflite-runtime

To load TFLite models, install the tflite-runtime package using:

pip install tflite-runtime

Installing tensorflow-gpu (For NVIDIA GPU Users)

Leverage GPU acceleration with NVIDIA GPUs by installing tensorflow-gpu:

pip install tensorflow-gpu

Note: Ensure you have compatible GPU drivers installed on your system.

Installing tensorflow (CPU Version)

For CPU usage or non-NVIDIA GPUs, install TensorFlow with:

pip install tensorflow

Usage

Follow these instructions to run YOLOv8 after successful installation.

Convert the YOLOv8 model to Int8 TFLite format:

yolo export model=yolov8n.pt imgsz=640 format=tflite int8

Locate the Int8 TFLite model in yolov8n_saved_model. Choose best_full_integer_quant or verify quantization at Netron. Then, execute the following in your terminal:

python main.py --model yolov8n_full_integer_quant.tflite --img image.jpg --conf-thres 0.5 --iou-thres 0.5

Replace best_full_integer_quant.tflite with your model file's path, image.jpg with your input image, and adjust the confidence (conf-thres) and IoU thresholds (iou-thres) as necessary.

Output

The output is displayed as annotated images, showcasing the model's detection capabilities:

image