From f5d50fa8c0e49cc75d21309b35857616c71c55e9 Mon Sep 17 00:00:00 2001 From: "Kin-Yiu, Wong" <102582011@cc.ncu.edu.tw> Date: Mon, 11 Jul 2022 18:20:53 +0800 Subject: [PATCH] main code update readme --- README.md | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index ed51998..9c2e5b5 100644 --- a/README.md +++ b/README.md @@ -73,12 +73,16 @@ To measure accuracy, download [COCO-annotations for Pycocotools](http://images.c ## Training +Single GPU training + ``` 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 ``` +Multiple GPU training + ``` 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 @@ -87,7 +91,6 @@ python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.p The training code and instruction of p6 models will release soon. - Download MS COCO dataset images ([train](http://images.cocodataset.org/zips/train2017.zip), [val](http://images.cocodataset.org/zips/val2017.zip), [test](http://images.cocodataset.org/zips/test2017.zip)) and [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip). If you have previously used a different version of YOLO, we strongly recommend that you delete `train2017.cache` and `val2017.cache` files, and redownload [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip) ## Re-parameterization @@ -109,6 +112,19 @@ The re-parameterization code and instruction will release soon. } ``` +## Teaser + +Yolov7-mask & YOLOv7-pose + +
+ ## Acknowledgements