When will SAM2/SAM3 training be available in Ultralytics?

Hi,

I noticed that SAM2 and SAM3 are currently supported in Ultralytics mainly for inference.

Is there any estimated timeline for when training or fine-tuning support will be released?

I’m interested in training SAM models on a custom dataset.

Thanks.

We currently don’t have plans to support fine-tuning for SAM. Is there any reason you are not able to use official repo for fine-tuning?

At the moment, there’s still no ETA for SAM2 or SAM3 training/fine-tuning support in Ultralytics.

Right now the support is inference-focused: the SAM 2 docs show Training as unsupported, and the SAM 3 docs currently cover predict and track workflows. So for custom SAM training today, the best path is still the official Meta implementation.

If you want, share your exact use case for fine-tuning and we can suggest the closest current workflow.