segment-anything
segment-anything copied to clipboard
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
i tested it on image & im getting the mask, now i want to save this mask/annotations in yolo or mask rcnn or any segmentation format. what should i need...
Thanks for your excellent work! I evaluate the object proposal generation of SAM (ViT-H) on LVIS v1, but the result of AR@1000 is 50.5 (not 59.3 reported in the paper)....
Thank you for the incredible work & congratulations! SAM does not seem to generalize as well on satellite imagery(tiny objects). This was the result of the "**segment everything**" option on...
i try to install on windows pycharm, but not able to running. so , i want know how to running on win10?
Finetuning
Is there any plans to release scripts for finetuning the model? Also you did such a great work! Thank you very much!
its like ?  
An Extraordinary work! Well, I try to export onnx, but error occurs. If opset=11, 12, 13, error message is: RuntimeError: Exporting the operator repeat_interleave to ONNX opset version 13 is...
Convert bounding box coordinates from (x, y, width, height) format to (x1, y1, x2, y2) format where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.
Hi, Thank you for the awesome work! I found this bug in the `apply_image_torch` function in the `utils/transforms.py` file. ``` def apply_image_torch(self, image: torch.Tensor) -> torch.Tensor: """ Expects batched images...
I would like to calculate embedding in a machine, then use it in another to do predictions. I have been trying to save it using predictor = SamPredictor(sam) predictor.set_image(img) embedding...