timmeinhardt/trackformer
Implementation of "TrackFormer: Multi-Object Tracking with Transformers”. [Conference on Computer Vision and Pattern Recognition (CVPR), 2022]
PythonApache-2.0
Issues
- 1
generate_coco_from_mot script does not converts SDP and DPM sequences from MOT17
#131 opened by Maxvgrad - 0
- 2
How to Prepare Custom Dataset for TrackFormer Multi-Object Tracking with COCO-Style Annotations?
#130 opened by userkw2 - 4
About MOT dataset PREV
#129 opened by Tsai-chia-hsiang - 1
About targets at training
#128 opened by Tsai-chia-hsiang - 0
Pretrained weight files
#127 opened by bluetooth12 - 17
I try to train with MOT17,when I use "multi_frame_attention = True",I get " RuntimeError: stack expects each tensor to be equal size, but got [2, 2, 21, 27, 43] at entry 0 and [2, 2, 21, 27, 42] at entry 1"
#95 opened by niangea - 0
How to use finetuned model for tracking?
#126 opened by ymoghadd - 0
"Training on MOT17, the parameters are incorrect."
#125 opened by 6xu6 - 4
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
#85 opened by niangea - 1
installation issues
#124 opened by vamsi-krishna-mishran - 2
How can we convert the model to onnx?
#99 opened by chenscottus - 0
Unexpected Random Track Prediction
#123 opened by nikeshdevkota - 1
Unknown CUDA arch (8.6) or GPU not supported
#117 opened by rumjie - 0
- 2
cannot allocate memory
#104 opened by jer1ry - 7
CUDA out of memory when the sequence last too long
#101 opened by czhaneva - 2
Why num_classes=20 in r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint_hidden_dim_288.pth?
#120 opened by imzhangyd - 5
The MOTP metrics is showing a low score.
#118 opened by nikeshdevkota - 0
The generation of trackid
#121 opened by zhoutianxiang-coder - 8
Issues related to track IDs
#119 opened by zhoutianxiang-coder - 7
Loading Data for Tracking
#113 opened by nikeshdevkota - 3
- 1
- 2
Please read & provide the following
#112 opened by zhoutianxiang-coder - 1
how to display the ID numbers
#115 opened by zhoutianxiang-coder - 1
- 8
- 0
Custom dataset: class_error: 0
#110 opened by nikeshdevkota - 0
Problems on running VisDrone2019 dataset
#109 opened by RicTimeMuseum - 0
- 11
Issues on training custom datasets
#106 opened by RicTimeMuseum - 2
- 2
Thoughts poor performance?
#103 opened by tadeegan - 6
Custom dataset: class_error: 100
#100 opened by dethresearcher - 0
Details of Pretrained model
#102 opened by MuzziKim - 4
How to generate segm results
#97 opened by niangea - 0
- 0
when I use evaluate_mot_accums to eva MOT17,I get "Process finished with exit code 137"
#93 opened by niangea - 1
Where to find checkpoints ?
#92 opened by maximereder - 2
ImportError: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory
#89 opened by hustmx721 - 0
Compare FPS with yolov7
#91 opened by trand2k - 1
Error While trying to run the demo code.
#88 opened by Bavesh-B - 9
I can not reproduce the results
#87 opened by loseevaya - 1
detections are not associated into the track
#86 opened by wshku - 4
ImportError: /home/simon/anaconda3/envs/trackFormer/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg/MultiScaleDeformableAttention.cpython-37m-x86_64-linux-gnu.so: undefined symbol: cudaSetupArgument
#84 opened by simonseo22 - 5
Please read & provide the following
#81 opened by niangea - 3
- 0
why use multi_frame_attention?
#83 opened by loseevaya - 2