From 85f8379a68193cd9a9298e31035f01d304ac21f9 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 26 Nov 2022 06:06:22 +0100 Subject: [PATCH] README Segmentation Usage fixes (#10298) Fixes per https://github.com/ultralytics/yolov5/issues/10288 Signed-off-by: Glenn Jocher Signed-off-by: Glenn Jocher --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 298e145..028a1c2 100644 --- a/README.md +++ b/README.md @@ -89,14 +89,14 @@ YOLOv5 segmentation training supports auto-download COCO128-seg segmentation dat ```bash # Single-GPU -python segment/train.py --model yolov5s-seg.pt --data coco128-seg.yaml --epochs 5 --img 640 +python segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 # Multi-GPU DDP -python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train.py --model yolov5s-seg.pt --data coco128-seg.yaml --epochs 5 --img 640 --device 0,1,2,3 +python -m torch.distributed.run --nproc_per_node 4 --master_port 1 segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 --device 0,1,2,3 ``` ### Val -Validate YOLOv5m-seg accuracy on ImageNet-1k dataset: +Validate YOLOv5s-seg mask mAP on COCO dataset: ```bash bash data/scripts/get_coco.sh --val --segments # download COCO val segments split (780MB, 5000 images) python segment/val.py --weights yolov5s-seg.pt --data coco.yaml --img 640 # validate