dongho Han

About visualization

1

Hello. Thanks for the nice project you've made. I got amazed by BundleTrack project, so I'm working with your code. But, I got stuck in the visualization part. Can you...

Problems with asset/models files

1

Hello. First, thanks for the nice work! I'm following your READEME explanation to make a new synthetic dataset, like OBMan. But while doing so, I got some problems. When I...

Hello! Thanks for the nice work! I really appreciate it. If it doesn't bother you, can you share the dataset, model files, ... in Google drive format, not the Baidu...

Using multi-GPUs

1

Thanks for nice work! I want to run `app.py` with multi GPUs due to GPU memory problem.. But if I change the line https://github.com/gaomingqi/Track-Anything/blob/e6e159273790974e04eeea6673f1f93c035005fc/app.py#L381 as, `args.device = "cuda:0,1,2"` like this,...

Hello, Thanks for your nice work! I wonder if I can run your model with, (1) SAM is substituted with SEEM(whole frame is segmented, not specific object), (2) After that,...

GPU Out of Memory Issue

6

When I try to evaluate with your code, I met GPU Memory Issue. Especially, running this code `CUDA_VISIBLE_DEVICES=0,1,2,3 mpirun -n 4 python entry.py evaluate --conf_files configs/seem/focalt_unicl_lang_v1.yaml --overrides COCO.INPUT.IMAGE_SIZE 1024 MODEL.DECODER.HIDDEN_DIM...

Hello! Thanks for the nice work! I really appreciate your work and try to reproduce the evaluation result. Can you share how to visualize the reconstructed hand? I couldn't find...

Hello! Thank you for the nice work! I really appreciate it. I'm curious about the qualitative results files you uploaded. I think GoPro test, REBlur test, REBlur addition -> all...