OmDet model The OmDet model was proposed in Real time Transformer based Open Vocabulary Detection with Efficient Fusion Head by Tiancheng Zhao, Peng Liu, Xuan He, Lu Zhang, Kyusong Lee from Om AI Lab. Github Repository If you like our model, please consider following our project on GitHub OmDet to receive updates and information about new model releases. We also invite you to explore our latest work on the Agents Framework OmAgent. Intended use cases This model is intended for zero shot (also called open vocabulary) object detection. Usage Single image inference Here's how to load the model and prepare the inputs to perform zero shot object detection on a single image: Batched images inference OmDet Turbo can perform batched multi image inference, with support for different text prompts and classes in the same batch:
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy