Skip to content

训练问题 #3

@lovekittynine

Description

@lovekittynine

您好,大概看了一下您的源码。您在训练的时候,train_op = tf.group([train_fc,train_net]),这个操作我没理解错的话,是不是先优化一次全连接层,然后优化一次整个网络。常规的做法不是先只优化全连接层,然后最后fine-tuing entire network吗?

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