Segmentation Model for Yolo v9 about yolov9 HOT 3 CLOSED

Code for multi-task will be release in the future.

from yolov9.

Hi, I wanted to ask the same.
The segment folder already exists and the train.py script looks similar to the yolov7 version to me.
Will you provide the yolo-seg.pt weights? Or can I use the pretrained weights provided for yolov7?
When I am trying to train from scratch with the provided yolov7-af-seg.yaml cfg file I am facing the following issue:

Traceback (most recent call last):
File "segment/train.py", line 646, in
main(opt)
File "segment/train.py", line 542, in main
train(opt.hyp, opt, device, callbacks)
File "segment/train.py", line 220, in train
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
KeyError: 'obj'

Edit:
By changing line 11: "dfl: 0.7" to "obj: 0.7" it seems to work now. Still some pretrained weights will be appreciated.

from yolov9.

Hi, I wanted to ask the same. The segment folder already exists and the train.py script looks similar to the yolov7 version to me. Will you provide the yolo-seg.pt weights? Or can I use the pretrained weights provided for yolov7? When I am trying to train from scratch with the provided yolov7-af-seg.yaml cfg file I am facing the following issue:

Traceback (most recent call last): File "segment/train.py", line 646, in main(opt) File "segment/train.py", line 542, in main train(opt.hyp, opt, device, callbacks) File "segment/train.py", line 220, in train hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers KeyError: 'obj'

Edit: By changing line 11: "dfl: 0.7" to "obj: 0.7" it seems to work now. Still some pretrained weights will be appreciated.

Hi dear
I have similar error, can you guide me to solve it?

from yolov9.