Tristan Walter

Using `crop_offsets` could be a way to set 0,0 to the same point - of course this only works if your data is otherwise quite similar. Meaning particularly that it's...

Hey, I realize this is late but - seems like your conda environment is broken? It says it cannot import keras from tensorflow. You could try out a beta version...

Hey there, unfortunately this does not really help me much in debugging this :( What version are you running? And it seems you are running it in cmd.exe. You should...

Hey, this is difficult to determine from the images alone. But, - posture_direction_smoothing should probably be disabled for now. this is more a bandate than a solution. the reason the...

This is a very good idea. Indeed I have something like that already in the software (with track_ignore/track_include + recognition_shapes + recognition_border). However, these do not fulfill the exact use-case...

I'm afraid I can't offer much help with this (other than emotional support), but I don't want to live without my colors... It's so puzzling that they wouldn't just add...

I have read the CLA Document and I sign the CLA

**recheck**

Oh wow, that is impressive! Who would've thought. Sorry about not testing it - I thought there would for sure be some kind of abstraction. I will do some testing...

What do you think of these changes instead: ```python downsampled_bboxes = bboxes.clone() scale_factors = torch.tensor([width_ratio, height_ratio, width_ratio, height_ratio], device=bboxes.device) downsampled_bboxes = downsampled_bboxes * scale_factors ``` ```python # Apply padding (if...