Skip to content

Single-label multi-classification or multi-label multi-classification? #7

@JingrongZheng

Description

@JingrongZheng

I have read the paper and it seemed to be a single-label multi-classification problem. But the code use BCE and sigmoid instead of crossEntropy and softmax. So does it mean that the patient may have more than one lung disease?(I want to confirm it since I am not a medical expert)

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