Error with training using Yolov8m

[GoharKhachatryan]

Hi! I wanted to train your algorithm using the yolov8m model. I used the downloaded weights as mentioned in the readme and the training command, only changing the model type into yolov8. I used the following command:
DATASET=visdrone MODEL=yolov8m GPUS=0 BATCH_SIZE=4 IMAGE_SIZE=1536 EPOCHS=10 bash ./scripts/train.sh
And got this error:
self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)) TypeError: __init__() got an unexpected keyword argument 'k'
The error was in a file ./models/common.py.
I think this is a problem with mismatch of the yaml file and downloaded weights, since your code supports only a yolov5 architecture.
I will be happy with any advice you could give. Thanks in advance!

[GoharKhachatryan]

If anyone has the same problem, the temporary solution I come up is the following: I used not the normal yolov8m weights from ultralytics, but the ones from the google drive of pre-trained models. This esod_yolov8m.pt works well with the visdrone_yolov5m.yaml config file, but still not with the v8 one. I think it is because the pre-trained weights are already modified to work with the v5 architecture. But I am not sure if this is still a solution.

[mahilaMoghadami]

thank you
where can I download esod_yolov8m.pt file?
appreciate your help.
and did you finally train yolov8m based on esod framework?