YOLOv8 (IGIE)

Model Description

Yolov8 combines speed and accuracy in real-time object detection tasks. With a focus on simplicity and efficiency, this model employs a single neural network to make predictions, enabling fast and accurate identification of objects in images or video streams.

Supported Environments

Model Preparation

Prepare Resources

Pretrained model: https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt

Dataset: http://images.cocodataset.org/zips/val2017.zip to download the validation dataset.

Install Dependencies

# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx

pip3 install -r requirements.txt

Model Conversion

python3 export.py --weight yolov8s.pt --batch 32

Model Inference

export DATASETS_DIR=/Path/to/coco/

FP16

# Accuracy
bash scripts/infer_yolov8_fp16_accuracy.sh
# Performance
bash scripts/infer_yolov8_fp16_performance.sh

INT8

# Accuracy
bash scripts/infer_yolov8_int8_accuracy.sh
# Performance
bash scripts/infer_yolov8_int8_performance.sh

Model Results