From 8f2e9e701cffaa7469435306e2f8a67ed4236e88 Mon Sep 17 00:00:00 2001 From: "Kin-Yiu, Wong" <102582011@cc.ncu.edu.tw> Date: Fri, 8 Jul 2022 17:04:00 +0800 Subject: [PATCH] main code update training instruction --- README.md | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index d0e96de..5ad0cee 100644 --- a/README.md +++ b/README.md @@ -67,7 +67,23 @@ You will get the results: ## Training -The training code and instrument will release soon. +``` +python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml + +python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7x.yaml --weights '' --name yolov7x --hyp data/hyp.scratch.p5.yaml +``` + +``` +python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml + +python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7x.yaml --weights '' --name yolov7x --hyp data/hyp.scratch.p5.yaml +``` + +The training code and instruction of p6 models will release soon. + +## Re-parameterization + +The re-parameterization code and instruction will release soon. ## Citation @@ -91,5 +107,7 @@ The training code and instrument will release soon. * [https://github.com/Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) * [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3) * [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5) +* [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG) +* [https://github.com/JUGGHM/OREPA_CVPR2022](https://github.com/JUGGHM/OREPA_CVPR2022)