The Geti models uploaded to https://huggingface.co/OpenVINO were all exported with a static batch size of 1, for example YOLOX-Tiny. In practice, clients cannot use these models for batch inference, an issue that's also discussed in ITEP-94275.
In scope of this ticket:
The Geti models uploaded to https://huggingface.co/OpenVINO were all exported with a static batch size of 1, for example YOLOX-Tiny. In practice, clients cannot use these models for batch inference, an issue that's also discussed in ITEP-94275.
In scope of this ticket: