Tobias Zaenker

I added support to read out the Chat-Mix dial. You can find the commit [here](https://github.com/Eruvae/HeadsetControl/commit/4ee8620b8165fca672fb26821885e4427f204313). If you want you can add it to this pull request, or I can create...

As long as the "publish_detections" parameter is set to true (which it is by default), the bounding boxes and masks will be published on the topic "/yolact_ros/detections". If you want...

As mentioned in my previous reply, you have to subscribe to ```/yolact_ros/detections```. If you renamed the node, the namespace changes. Do you get output for ```rostopic echo /yolact_ros/detections```? If not,...

I don't use docker, so I can't provide that. Feel free to contribute one. However, I'm not convinced a dockerfile for a single ROS package is a good idea. If...

[YolactEdge](https://github.com/haotian-liu/yolact_edge) supports TensorRT, so you could try setting that up and then using the yolact_edge_ros script that I added for issue #16. I have not used it myself though, so...

@crNewton The masks are stored as bit arrays packed with numpy's [packbits](https://numpy.org/doc/stable/reference/generated/numpy.packbits.html) function. To revert the process, you can use the [unpackbits](https://numpy.org/doc/stable/reference/generated/numpy.unpackbits.html) function. You should be able to use it...

Since nothing is printed before the segmentation fault, this seems to happen before it is attempted to load the model. You can try using the faulthandler module to find out...

rosrun yolact_ros yolact_ros is the correct way to run it. The error seems to happen during the initialization of a layer from Yolact. Which model are you using? I would...

I've updated the readme with usage instructions now and changed the default model to yolact_base.

That's a pretty old version. I tested downgrading to it and also got errors. Try upgrading to torch 1.4.0 with the command above and check if it works then.