Tim Meinhardt
This looks like an error not specific to this repository. Please check if your setup is working!
This is not implemented. You have to add this to the codebase.
This might indeed be a bug. We never tested the codebase for sequences with that many frames. During inference all previous tracks are kept in the memory. For 10000 or...
@HenryZhou19 This is not the same problem as mentioned in the first message of this issue. The original problem was a CUDA out-of-memory issue during inference not training.
1. The README says it can be **trained** without code changes. ;) But yes, to run an evaluation one has to add the dataset to the code in the `factory.py`...
The data annotation is definitely the right place to look at. This could be due to wrong label indices for the background. The `datasets/coco.py` expects the person label to be...
The code might load the detection results but it is not using it. For a quick fix you can put your ground truth files and detections and then run private...
Did the manual compiling of the `MultiScaleDeformableAttention` module finish without errors? And did the test run through?
Is this the output from the first install or a second execution? The second one might not show the same errors as the first one. So you need to uninstall...
We provide the MOTS20 results for the old model cause the deformable attention seemed to perform worse for segmentation. Multi-frame and multi-scale trainings were not part of the old model....