Skip to content

Inference time #8

@gongshichina

Description

@gongshichina

Hi, In my experiment, the inference time of PeleeNet is 3 times larger than ResNet18, and is almost equal to ResNet50 ?
I guess the reason is I didn't use TensorRT which can optimize the RAM access. Could you please give a more detailed explanation?

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