RMOT
RMOT copied to clipboard
wudongming97
[CVPR2023] Referring Multi-Object Tracking
Why do I get an error when batchsize is set greater than 1? If batchsize=1, then what's the point of training multiple cards
Hi, Developer team. I have encounter some problems when i try the testing part. Below are some outputs from the command line No param transformer.decoder.layers.0.update_attn.in_proj_weight.If you see this, your model...
As it can be seemed here: ```bash root@tony:~/449_RMOT/exps/default$ ls checkpoint0099.pth root@tony:~/449_RMOT/exps/default$ cdd root@tony:~/449_RMOT$ sh configs/r50_rmot_test.sh Training with Extra Self Attention in Every Decoder. Training with Self-Cross Attention. Namespace(accurate_ratio=False, append_crowd=False, aux_loss=True,...
**train:** loaded ./data/r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint.pth Skip loading parameter class_embed.0.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you...
Hello, thank you very much for your great work! I would like to know more details about your dataset labeling method and the annotation tool you mentioned in the paper,...
Hello the authors, your work is amazing and interesting. When following your code, I cannot find a place to calculate the metrics, could you give some hints? I appreciate your...
NKF in the paper, which corresponds to that part of the code? I'm a beginner and I don't understand the NKF part of the code. @wudongming97
Why are the json files of the "persons in the right" and "persons in the left" in video 16 exactly the same when the two expressions mean opposite things? Could...
Subsequent articles indicate that the reports results after frame correction. I don't know whether your current dataset is modified
Dear Dr. Wu , I hope this email finds you well. I am writing to seek your assistance in understanding the structure and meaning of a JSON file located in...
