To prepare a custom model for upload to HubAI, we need to prepare its Model File(s) and Model Card.
Model File(s) Preparation
Train a model of choice or obtain an existing model of interest.
If the model is in ONNX (.onnx), OpenVINO IR (.xml and .bin), or TensorFlow Lite (.tflite) format, you can skip this step. If the model is one of the supported PyTorch YOLO models, you can also skip this step. Else convert it to one of the formats mentioned above. For more information, see the guidelines in the Model Source Preparation section on the Model Conversion page.
Optionally, package the model file(s) it into a NN Archive. This will ease the model conversion for the appropriate RVC platform.
Supported PyTorch YOLO Models
At the moment, we support the conversion of YOLOs ranging from V5 through V11 and Gold Yolo including oriented bounding boxes object detection (OBB), pose estimation, and instance segmentation variants of YOLOv8 and YOLO11. Please note we support the conversion of YOLOv9 weights only from Ultralytics.
Model Card Preparation
Model card can be abribtrary for private (team-owned) models. For public models, however, it should follow the structure and contain the information described in the Model Card section on the HubAI Concepts page. It's adviced to consult the model release paper, GitHub repositories, and other relevant resources to obtain the required information. To get a better idea of the Model Card structure and what infromation should be included, we suggest to check our Model Card Template or to take a look at Model Cards of the existing HubAI entries.