About reproducing the paper

Hi @nikitakaraevv,

Thank you for your excellent work.

I have a question regarding the training pipeline. I'm currently trying to reproduce the results in Table 3 of your paper. When I trained the model from scratch on the Kubric dataset, the best evaluation result on the Tapvid Davis dataset is as follows:

"occlusion_accuracy": 0.8503666396802487
"average_jaccard": 0.5575681919643163
"average_pts_within_thresh": 0.7087581437592014
These results are significantly lower than those obtained with your provided checkpoint. I'm using Torch 2.1.0 with CUDA 12.3, and trained the model on 8 A100 GPUs with 200000 iterations, and accumulate gradient of 4 to mimic your setting.

Do you think the issue could be due to mismatched library versions, or might I be missing something else? I appreciate any guidance you can provide.

Thank you.

The issue names no files, tests, or entry points. Start by comparing the Kubric training run using Torch 2.1.0, CUDA 12.3, 8 A100 GPUs, 200000 iterations, and gradient accumulation of 4 with the provided checkpoint, then evaluate on Tapvid Davis; done means explaining the gap or reproducing the Table 3 results.

Written by the indexing model from the issue text.