-
Missing 'scene0789_00', 'scene0792_00', 'scene0806_00' for testing dense captioning, is predictions on these scenes required?
-
Hi, thanks for the excellent work! I got some questions about this project.
1. I noticed that there exist some unanswerable samples in the val set, Since we treat this QA problem as the multi-classi…
-
What's the code for submitting results on official benchmark?
https://kaldir.vc.in.tum.de/scanrefer_benchmark/benchmark_captioning.php?sortby=dmAP_0_5
It would be helpful if related codes are sh…
-
I find a visualization code in [ScanRefer](https://github.com/daveredrum/ScanRefer/blob/master/scripts/visualize.py). Did you use this code to visualize your results?
-
Hi,
Thanks for sharing the code! Can I know how large is the computation? Is is computation expensive to do 3D visual grounding?
-
Hi, I'm really interested in this work. But I cannot follow the Data preparation. It seems lack of the instruction for SCAN2CAD dataset.
-
Besides, why not directly integrate the data folder from ScanRefer into your repo?
-
I have successfully trained the model, but when I try to evaluate the result, it reported an IndexError to me. It seems that the shape of mask[i] didn't align with the shape of ref_acc[i], but I have …
-
微博内容精选
-
Running the training program on a single RTX3090 will encounter the out of memory problem. Thus, I run the code in the distributed mode with 2 RTX3090, and the batchsize is 16 for each GPU(total batch…