I keep getting the error “Oops something went wrong, there might be issues with this model” when trying to use the model in roboflow.
It’s a yolov8 segmentation model, trained with the exact version of ultralytics required. It works easily on my machine on CPU and GPU. The upload of the model went well, I’ve tried it with different version.
It’s only when TESTING the model IN roboflow that the error occurs, which makes the use of the model for later segmentation impossible.
Project Type: Object Détection
Operating System & Browser: Windows, google chrome
Project Universe Link or Workspace/Project ID: money_detector-j1nx5
Here’s the python code I used to train the model :
from ultralytics import YOLO
model = YOLO(‘yolov8n-seg.pt’)
model.to(‘cuda’)
if name == ‘main’:
results = model.train(
data=‘money_detector.v3i.yolov8/data.yaml’,
epochs=200,
imgsz=640,
batch=4,
device=‘cuda’,
single_cls=False,
lr0=0.0001,
overlap_mask=True,
mask_ratio=4,
mosaic=1.0
)
And here’s the code I used to deploy the model to Roboflow :
from roboflow import Roboflow
rf = Roboflow(api_key=“myProjectKey”)
project = rf.workspace().project(“money_detector-j1nx5”)
version = project.version(“3”)
path = “my/path/to/where/the/model/reside/”
version.deploy(model_type=“yolov8”, model_path=path, filename=“money_seg_3.pt”)