diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md
index fbc0b9e70322fc23363c3368883d100f8ad68ac5..089b3b8f40e6af7bc10b0c0191bf553be8812ddd 100644
--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
@@ -14,7 +14,6 @@
   * [3.1 指标评估](#31-----)
   * [3.2 测试检测效果](#32-------)
 - [4. 模型导出与预测](#4--------)
-  * [4.1 转inference模型测试](#41--inference----)
 - [5. FAQ](#5-faq)
 
 <a name="1--------"></a>
@@ -207,9 +206,6 @@ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./
 <a name="4--------"></a>
 # 4. 模型导出与预测
 
-<a name="41--inference----"></a>
-## 4.1 转inference模型测试
-
 inference 模型（`paddle.jit.save`保存的模型）
 一般是模型训练，把模型结构和模型参数保存在文件中的固化模型，多用于预测部署场景。
 训练过程中保存的模型是checkpoints模型，保存的只有模型的参数，多用于恢复训练等。
diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md
index bdfde6720df82f4773459792e031b99fd030bdb9..016cf929283c0b8dac5cd1f0b3c808c398186917 100644
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
@@ -13,7 +13,6 @@ This section uses the icdar2015 dataset as an example to introduce the training,
   * [3.1 EVALUATION](#31-evaluation)
   * [3.2 TEST](#32-test)
 - [4. INFERENCE](#4-inference)
-  * [4.1 INFERENCE MODEL PREDICTION](#41-inference-model-prediction)
 - [2. FAQ](#2-faq)
 
 # 1 DATA AND WEIGHTS PREPARATIO
@@ -200,8 +199,6 @@ python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./
 
 # 4. INFERENCE
 
-## 4.1 INFERENCE MODEL PREDICTION
-
 The inference model (the model saved by `paddle.jit.save`) is generally a solidified model saved after the model training is completed, and is mostly used to give prediction in deployment.
 
 The model saved during the training process is the checkpoints model, which saves the parameters of the model and is mostly used to resume training.