paddle Macro-F1

Paddle的Macro-F1指标是用来评估预测句子相较于ground truth中实体的重复率的一种方法。在计算Macro-F1时，首先计算每个样本的F1值，然后对所有样本的F1值求平均得到最终的Macro-F1值。F1的计算公式为F1=2*(Precision*Recall)/(Precision+Recall)，其中Precision代表准确率，Recall代表召回率。因此，Paddle的Macro-F1可以通过计算每个样本的准确率和召回率，再求平均得到。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* [评价指标F1之Mirco-F1和Macro-F1](https://blog.csdn.net/ChinaZm/article/details/124340548)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
- *3* [PaddleDetection-release-2.51，PaddleDetection源码包](https://download.csdn.net/download/weixin_44906759/87359252)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]