Bo Wang

Hyperparameters of several finetuning experiments

2

Thank you for your great work! Could you give the hyperparameters (like **learning rate**, **batch size**, **crop size**, and **step number**) that can reproduce the paper data in three finetuning...

Nice work! By the way, it seems that there is no description of batch size number during finetuning on KITTI and ETH3D in the paper. And it also does not...

About the training window size of stride 8 model.

1

Nice work! What are the training window sizes for the stride8 models in Table 7 of Paper v1 and Table 9 of Paper v2, respectively? Best regards

About reproduction of training.

1

Hi, the work is excellent. I am equipped with merely eight 24GB 3090 GPUs. I am utilizing the code from Cotracker1 for training, attempting to reproduce the performance under 'stride8...