Skip to content

转tf,进行测试 #19

@PC-god

Description

@PC-god

您好,我把darknet的网络和权重拿出来之后。最后一层的输出是logit层么 也就是未经logistic的,那么预测的时候
对'table/convolutional33/BiasAdd' 需要logistic么,还是类似 函数 dnn_table_predict 里 exp的操作

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