TransTrack
TransTrack copied to clipboard
PeizeSun
Multiple Object Tracking with Transformer
Hello, I'm trying to reproduce results on MOT20, but I got a 5 points drop using the default hyper-parameter from MOT17. Can you provide the training script on MOT20?
HI, could you release some instructions on training on coco dataset? Thanks a lot!
Issue #22 [https://github.com/PeizeSun/TransTrack/issues/22#issue-884151001](url) Similar to the bugs faced in the previous closed issue, has anybody figured a way of exporting the model to ONNX? Have you guys tried to create...
加载671mot17_crowdhuman_mot17.pth模型后，推理的视频中基本没有检测框，当阈值设成0后，才会出现满屏矩形框。 我的参数这样设置的python demo.py --device cuda --video_input videos/palace.mp4 --demo_output output/ --track_thresh 0.4 --resume pretrained/671mot17_crowdhuman_mot17.pth
When i test my demo. I find frequently an object is surrounded by more than one regression box. So i find you didn't delete overlap regression box. Why you didn't...
I trained custom data according to the format of MOT17 label file, using classification labels from 1 to 4, but I got an error.It illustrates "Assertion idx_dim>=0 && idx_dim
HELLO, when running the codes, an error raised as follows: **_D11 COMPILER TYPE=" gCC" -DPYBIND11 STDLIB-" libstdcpp" -DPYBIND11 BUILDABI-" cxxabi1011"-DTORCH EXTENSIONNAME=MultiScaleDeformableAttention -D_GLIBCXX_US E CXX11 ABI-0-std=c++14 cc1plus: warning: command line option'-Wstrict-prototypes’is...
i use this code ,when i run `python setup.py build install` ,it return me error like title, my gcc is like this `Using built-in specs. COLLECT_GCC=gcc COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/9/lto-wrapper OFFLOAD_TARGET_NAMES=nvptx-none:hsa OFFLOAD_TARGET_DEFAULT=1 Target:...
Hello, I want to run the code. So, at first I built the MultiScaleDeformableAttention Module and it is installed successfully. ``` (virenv) mohammadh@ut-cavlab:/hdd/nasseri/TransTrack-main/models/ops$ python3 setup.py build install --install-lib='/hdd/nasseri/virenv/bin' running build...
