Luming Tang
Luming Tang
Hi, I saw the default setting (both the eval.py and the evaluation command-line script in the ReadMe file) is using opencv solver. However, for 5-shot evaluation, the structured FC weights...
Hi thanks a lot for your previous detailed response and it's really helpful. However, I am still quite confused about the details in table 3c. In the last post, u...
For tiered imagenet, I noticed that in the validation step during training, the args.enlarge is set to False/None because there's no '--enlarge' in the training configs. However, in the evaluation/testing...
Hi, thanks for your great work! I am just wondering is this an online tracker or an offline tracker? After the reading of the whole paper, I feel like this...
Hi, thanks for the great work! We implemented the update-bias-only transfer learning in our own codebase, however, we didn't notice a huge decrease of peak memory / memory usage during...
Hi Mark, Thanks for the great work! And I really like the correspondence demo you showed in the video. I am just wondering is `plot_dino_correspondence.py` used to reproduce that? If...
* K3D version: 2.14.5 * Python version: 3.9 * Operating System: ubuntu ### Description When I try to run k3d in my jupter lab, I got the following error messages:...
hi, thanks a lot for your code! Everything works well when I only use one gpu by setting cuda_visible_devices=0 (for example), but when I use multiple gpus by setting cuda_visible_devices=0,1...
Hi, thanks for the great codebase! When I ran the setup, I noticed that for the first 1k iterations, the loss value is always displayed as 0. And after that,...
Hi, thanks a lot for the great codebase! I noticed the current default setup is one single-view image per training iteration. I am just wondering how we could increase the...