I am facing the same issue as#283 and despite the resolution mentioned I was not able to resolve the problem of incorrect bounding box.
I am using cuda 11.8, torch 2.2.0 on Ubuntu 22.04 and RTX 4060 GPU.
I have also fixed all the issue like #298 and the results of running
python run.py --type evaluate --cfg_file configs/linemod.yaml model cat cls_type cat test.vsd True
Load model: data/model/pvnet/cat/199.pth
loading annotations into memory...
Done (t=0.15s)
creating index...
index created!
loading annotations into memory...
Done (t=0.02s)
creating index...
index created!
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1002/1002 [00:34<00:00, 28.87it/s]
2d projections metric: 0.39520958083832336
ADD metric: 0.09181636726546906
5 cm 5 degree metric: 0.1407185628742515
mask ap70: 0.041916167664670656
But the when visualising
python run.py --type visualize --cfg_file configs/linemod.yaml model cat cls_type cat
I get the following output
I am facing the same issue as#283 and despite the resolution mentioned I was not able to resolve the problem of incorrect bounding box.
I am using cuda 11.8, torch 2.2.0 on Ubuntu 22.04 and RTX 4060 GPU.
I have also fixed all the issue like #298 and the results of running
python run.py --type evaluate --cfg_file configs/linemod.yaml model cat cls_type cat test.vsd True
But the when visualising
python run.py --type visualize --cfg_file configs/linemod.yaml model cat cls_type cat
I get the following outputOriginally posted by @utsavrai in https://github.com/zju3dv/clean-pvnet/issues/282#issuecomment-2119281037