olinesn
olinesn
Hello, this is a feature request for future versions. When iterating in frame-by-frame mode, it looks like roughly 30 frames are loaded at a time in blocks. When I reach...
When proofreading a .slp file, I'll often update the position of the subject's nose, which has a higher error rate than other nodes. I also leave the Trail Length at...
Hello, I've got a bug when using the 1.2.0a6 build: When dragging a node, if you change frames before you've release the node (still holding left click) and then release...
**Problem:** We only allow for filtering based on instance score during tracking. We should have options for filtering even without tracking (e.g., during the HITL labeling process). **Solution:** Add `Predictor`...
Hello, It would be great if when picking model training options like Max Stride and Input Scaling, we could flip through a random subset of example frames rather than seeing...
**Problem:** There are many features that could be visualized with the tracks display that can help with proofreading and other applications. **Desired functionality:** - Trail visualization options might need to...
**Problem**: Some frames may not contain any instances, but we might explicitly want to train our model to output all zero confidence maps for these so we don't get any...
# Bug description This bug showed up in 1.2.7 and 1.2.8, but I've tested 1.2.6 and earlier and it is absent in those versions. When editing inferred skeletons, changing the...
Hello, I'm having difficulty running calibration with my camera setup. I have 7 cameras, and two of them are pointed inward in such a way that they rarely / never...
# Bug description When running inference, the GPU starts using system memory (as seen in the task manager) until there's none left, and then inference crashes. You can see that...