Yongqi An

> Hello! I really like this project. Do you plan to support splitting this model into Encoder and Decoder like the original SAM? In that way, the Decoder part can...

> We can also convert the model to ONNX to remove the dependence on PyTorch, which has a very big size compared to ONNXRuntime. My code for the original SAM...

Thanks very much for all of you for your attention! **Training and fine-tuning codes will be put together and released soon!** > Hey, Huge thanks for such a great repo...

The code is currently being organized to optimize its utility for downstream task fine-tuning scenarios. If you wish to promptly obtain the code for training or fine-tuning purposes, kindly reach...

> I handled it. You can reference at link: [GitHub] (https://github.com/ChuRuaNh0/FastSam_Awsome_TensorRT). If it helpful with you, give me a star, thanks. Thanks for your contribution! We will add [FastSAM_Awesome_TensorRT](https://github.com/ChuRuaNh0/FastSam_Awsome_TensorRT) link...

Of course, we would love for you to have a try! **Training and fine-tuning codes will be put together and released soon!** > Hi author, Will you release the code...

@machine52vision Please wait for a moment. **Fine-tuning code will be released soon!**

We would close this issue for now to keep the issue tracker organized. However, if the problem persists or if you have any further questions, please feel free to comment...

Thanks for your attention. We will test the 1920*1080 image to find and fix the problem now. BTW, the segmentation result is really beautiful :) > Actually, the output image...

> You can try to use Grounding-DINO to generate box prompt for this situation, we have already implemented this in [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything/tree/main/FastSAM) @pepijnob @rentainhe Thanks again for helping us to combine...