Skip to content

About dataset used for training and test #1

Description

@xlbjy

Hi, nice work! It looks like the dataset is very large, with 1.2TB of raw data and 41TB of processed data. Do I need to use all the data if I want to get the results in the paper? Moreover, which GPUs are you using for training? Is it a single-GPU training? What is the approximate duration of the training? Thank you very much.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    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