Skip to content

请问能否在cuda/gpu上实现share memory? #29

@DreamerSurpass

Description

@DreamerSurpass

您好,您在continuous_A3C代码中使用cpu进行并行的计算,我发现若将gnet放置于cuda上,在process.start()后,gnet初始化的weight会都变成0,这是什么原因呢?是否能在gpu上进行share的操作呢?
在w.start()之前
image
在w.start()之后
image

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions