Brad Dwyer

Hi, we're probably going to deprecate this repo soon in favor of https://github.com/roboflow/inference given that it should do everything this does & lots more easier and more efficiently.

You should be able to define a skeleton (point names and which vertices are connected to each other and ideally their colors). I don't think having separate things for Human...

Thanks for the submission @duke194; we've been holding off on merging for the time being because I think [this PR in Supervision](https://github.com/roboflow/supervision/pull/353) will address this in a way that doesn't...

> I have added the package to PyPI. Will try to get it on conda-forge as well. I would be happy add maintainers to the package if anyone is interested....

> The GPU installation is handled by torch-gpu, so GroundingDINO does not have to handle it. GroundingDINO has these custom C++ and CUDA files: https://github.com/IDEA-Research/GroundingDINO/tree/main/groundingdino/models/GroundingDINO/csrc Are the compiled versions of...

> It would be great if GroundingDINO can make the installation a bit more smooth. There are many installation related issues reported here, and I spent hours trying to install...

As a followup, I ran a benchmark: * Installing via cloning the repo (A100 on Colab): 100 inferences in 19.1 seconds (5.2 fps) * Installing via cloning the repo (CPU...

We added support in Roboflow for [annotating using SAM](https://blog.roboflow.com/label-data-segment-anything-model-sam/). We convert the masks to polygons & you can export to YOLO format for training a model.

Looks like you’re not converting to polygons very well. You have points that lie outside of your core shape, your shape doesn’t start and end near the same spot, and...

I don't know how to do it in Python; as noted above, [we built SAM into Roboflow](https://blog.roboflow.com/label-data-segment-anything-model-sam/) & [you can export your dataset in YOLO format](https://blog.roboflow.com/how-to-train-yolov8-on-a-custom-dataset/).