Skip to content

Do we need to subtract mean pixel values when extracting cnn feautre #65

@danieljf24

Description

@danieljf24

Hi! I followed this notebook to extract image feature using pre-trained CNN model. I wonder do we need to subtract mean pixel values of imagenet before feature extraction. Other deep learning frameworks usually have this process, but I didn't find it in this notebook.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions