Skip to content

About parameters to reproduce the result on paper #15

@Robert-JunWang

Description

@Robert-JunWang

We trained on the FlyingThings dataset using 8x A5000 GPUs with the following command:
python -m torch.distributed.launch --nproc_per_node=8 --master_port=29501 train.py \ --checkpoint_dir $YOUR_CHECKPOINT_DIR \ --stage things \ --val_dataset things sintel kitti \ --batch_size 256 \ --num_workers 8 \ --lr 8e-4 \ --val_freq 500 \ --distributed

So the model is trained for 1000k steps on things with batch size 256?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions