clausMeko
clausMeko
I often have this issue if a file mentioned in `tables.yaml` or `functions.yaml` doesn't exist in the file system or is named differently. Actually a **more precise error message** would...
I would also really like to have it supported officially as I have the same use case as @innix. For now would I need to use v1.
I can reproduce this. The only thing I could do to fix it is edit metadata/remote_schemas.yaml by hand.
Is this still an issue? If so maybe only in SQLite? I am using postgres where it works as expected. So maybe update the Issue to include `... on sqlite`?
Model Type: Roboflow 3.0 Instance Segmentation (Accurate) Is that what you mean?
You mean from my login - its not public? `emerald-fbdh0/4`
Ty, In parallel you could name me a public model with some expected performance so I can see if my setup is in general as fast as expected.
@PawelPeczek-Roboflow It is **still 5 FPS**, i.e. 200ms/image on the the public model. I added some info. So somehow I am stuck with 5FPS on an Orin Nano. I am...
@yeldarby your proposed Model `yolov8n-640` runs at ~6fps on my orin nano. @PawelPeczek-Roboflow I checked what a reduced resolution changes. ```python client = InferenceHTTPClient( api_url="http://localhost:9001", api_key=ROBOFLOW_API_KEY, ) # 100 times...
@PawelPeczek-Roboflow so you would recommend choosing **object detection** over **segmentation** models if it is about performance?