Ruslan Murtazin

I've notice export works if I click on every image in gallery

No, it still doesn't work, I can't draw a bbox after create new anno on image

I'm trying now but getting another error. (TracKit):~/TracKit$ python tracking/test_ocean.py --arch OceanTRT --video videos/1.mp4 Traceback (most recent call last): File "tracking/test_ocean.py", line 29, in from lib.core.eval_otb import eval_auc_tune ModuleNotFoundError: No...

I've got this one: (TracKit):~/TracKit$ python tracking/test_ocean.py --arch OceanTRT --video videos/1.mp4 OceanTRT( (features): ResNet50( (features): ResNet_plus2( (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)...

I run in environment "TracKit", I didn't create another one like "OceanOnlineTRT"

(TracKit) kfour@kfour:~/TensorRT-7.0.0.11/python$ pip install tensorrt-7.0.0.11-cp37-none-linux_x86_64.whl Processing ./tensorrt-7.0.0.11-cp37-none-linux_x86_64.whl tensorrt is already installed with the same version as the provided wheel. Use --force-reinstall to force an installation of the wheel.

I just found this one: https://forums.developer.nvidia.com/t/attributeerror-nonetype-object-has-no-attribute-create-execution-context/110199/5 First row of error: [TensorRT] ERROR: INVALID_CONFIG: The engine plan file is generated on an incompatible device, expecting compute 6.1 got compute 7.5, please...

I googled else and understood I need to rebuild the engine for my GPU, do you have any ideas how to do it? I've found that: https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#build_engine_python

I have H100, it still works so slow

Hi! How'd you install Pytorch3d?