EdgeSAM

EdgeSAM copied to clipboard

Does your model not support torch.jit? I encounter an error when trying to convert the model with the following code. If there is a solution, please let me know. ```python...

stjbb

License

3

Hi thanks for your work, I would like to ask if the license will also apply for the model itself intended as weights values or is only applicable to code,...

eric-tc

Thanks for your great work. Our C++ code corresponded to your Edge SAM models. Here is the [Segment Anything CPP Wrapper for macOS](https://github.com/ryouchinsa/sam-cpp-macos/tree/master). Please ask about your license. We are...

ryouchinsa

As mentioned in the title and how?

zpge

I'd like to finetune EdgeSAM for a specific task. Is there code already available? Have you experience in finetuning EdgeSAM?

a333klm

Decoder CoreML running time problem

3

When running the decoder with the same number of points time after time, the running time may approach the number reported by the performance analysis of Xcode. However, this is...

benjamin-kramer

Query on ONNX Encoder Inference Time: Samsung A20 with Android 11

1

The performance demonstrated in the paper for the iPhone 14 is remarkable, and I'm currently attempting to evaluate the model on an entry-level Android phone. In a basic implementation, the...

karamazvo

Hello! I'm interested in following your work. May I kindly inquire whether the code you use for training will be made open source? Thank you.

zoeccolor

when i change the code as: ``` def export_decoder_to_onnx(sam, args, batch_size=4): sam_decoder = SamCoreMLModel( model=sam, use_stability_score=args.use_stability_score ) sam_decoder.eval() if args.gelu_approximate: for n, m in sam.named_modules(): if isinstance(m, torch.nn.GELU): m.approximate =...

yanzongs

Added more information on how to download the rep_vit weight. Also, the correct version is repvit_m0_9 not repvit_m1_0.

SimonZeng7108