Problems when parsing model metadata using inferencejs

Community Help
1
  • **Project Type: Instance segmentation
  • **Operating System & Browser: Windows, Firefox
  • **Project Universe Link or Workspace/Project ID: Sign in to Roboflow

Hello everyone. I am currently running into this error when I try to run my model through inferencejs: Error: Error loading model spectrogram-4ah9q/instance-segmentation-for-images/2: Error: Error happened while parsing model metadata. {}
Below is the code I use for inference. I custom train my model locally then I upload my trained model to roboflow using deploy function in roboflow in python.
Has anyone ever run into this problem before and how one can solve it?

code for ML
code for ML1159×323 17.6 KB

2

Unfortunately, inference.js doesn’t currently support instance-segmentation models. Try hitting our hosted API with a post request, or standing up your own api in a couple commands using our inference docker container

pip install inference-cli
inference server start
3

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.