Skip to content

损失函数问题 #34

@xswings

Description

@xswings

感觉这个损失函数是不是有点问题啊,tf.reduce_sum(cost) / tf.to_float(batch_size),分子是cost的和,分母怎么会是batchsize?不应该是tf.reduce_sum(loss_mask)么?

Metadata

Metadata

Assignees

No one assigned

    Labels

    questionFurther information is requested

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions