Ryo Kawamura

Improved "Create polygon using SAM" feature so that you can label pixels using the pixels option. You can label [Segment Anything 1 Billion (SA-1B)](https://ai.meta.com/datasets/segment-anything-downloads/) like dataset by yourself. 

We are running ONNX models using the [Segment Anything CPP Wrapper for macOS](https://github.com/ryouchinsa/sam-cpp-macos#segment-anything-cpp-wrapper-for-macos).

Thanks for writing the issue and I am sorry for late reply. According to this user, the CPP Wrapper works on the iOS project. https://github.com/ryouchinsa/sam-cpp-macos/issues/1#issuecomment-1779779964 [MobileSAM ](https://github.com/ChaoningZhang/MobileSAM) will be fast...

There are 2 steps to realize the smart polygon feature. Dragging a box, apply an segmentation model and the segmentation mask is obtained. Using cv::findContours(), convert the mask to the...

We know that Supervisely is one of the greatest online image annotation tools. [RectLabel](https://rectlabel.com) is an offline image annotation tool for object detection and segmentation. Although this is not an...

Thanks for your kind feedback. This is our roadmap to evolve RectLabel. Please let us know your opinion. 1. Correspond to ONNX models for auto labeling such as EfficientSAM, EdgeSAM,...

Thanks for writing the issue. Thanks for introducing the CoreMLPlayer and we checked how it works. We will implement your feature requests one by one. 1. Frames per a second...

I am sorry for late reply. The new version 2023.12.08 was released. Improved so that when converting video to image frames, you can set frames per second. I will implement...

Thanks for writing the issue. We will support the Linux version. We are having a feature request for the Ubuntu version. They say most of the people working with PyTorch/TensorFlow...

Thanks for writing the issue. I will do my best to reproduce the problem in my environment. Which annotation format are you using when save? PASCAL VOC xml or YOLO...