Fine-tuned weights

🤝 Community Help
1

Dear All,

we have core plan. Must use Roboflow inference for speed.

The weights we download seems to be basic, not fine tuned. We can see difference when using API. Where can I find the fine-tuned weights so we can run the model locally?

We have Core-plan.

Thanks.

2

Hello again,

can someone please help? Where do I find the correct weights so we can use Roboflow inference (run locally on a computer)?

Thank you.

3

Hi @EE_2026

The weight downloads from train should be identical to the trained model we use for inference. Would you be able to send over some of the code you are using to run inference? I am happy to take a look to see if something jumps out. Also would you be able to clarify if you are having issues with latency or accuracy when running locally verses running with the API.