From d2be5b0b6900a1623e71adc586419a56e16c5a18 Mon Sep 17 00:00:00 2001 From: hufangjian Date: Tue, 27 Feb 2024 13:27:39 +0800 Subject: [PATCH] add yolov8 paddle --- cv/detection/yolov8/paddlepaddle/README.md | 39 ++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100755 cv/detection/yolov8/paddlepaddle/README.md diff --git a/cv/detection/yolov8/paddlepaddle/README.md b/cv/detection/yolov8/paddlepaddle/README.md new file mode 100755 index 000000000..5ca2c42a3 --- /dev/null +++ b/cv/detection/yolov8/paddlepaddle/README.md @@ -0,0 +1,39 @@ +# YOLOv8 + +## Model description + +YOLOv8 is the world's most loved vision AI, representing Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development. + +## Step 1: Installation + +```bash +cd deepsparkhub/cv/detection/yolov8/paddlepaddle/ +git clone -b release/2.7 https://github.com/PaddlePaddle/PaddleYOLO.git +cd PaddleYOLO/ +pip3 install -r requirements.txt +python3 setup.py install +``` + +## Step 2: Preparing datasets + +```bash +python3 dataset/coco/download_coco.py +``` + +## Step 3: Training + +```bash +# Make sure your dataset path is the same as above +export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 +# Select $config_yaml from "configs/yolov5" as you wish +config_yaml=configs/yolov8/yolov8_s_500e_coco.yml +python3 -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c ${config_yaml} --amp --eval +``` + +## Results +GPUs|Model|FPS|ACC +----|---|---|--- +BI-V100 x8|YOLOv8-s| 20.0911 images/s | bbox ap: 0.259 + +## Reference +- [PaddleYOLO](https://github.com/PaddlePaddle/PaddleYOLO) -- Gitee