diff --git a/README.md b/README.md
index ed1bf494..2145e612 100644
--- a/README.md
+++ b/README.md
@@ -76,8 +76,8 @@ python tools/eval.py --data data/coco.yaml  --batch 32 --weights yolov6s.pt --ta
 Export as ONNX Format
 
 ```shell
-python tools/export_onnx.py --weights yolov6s.pt --device 0
-                                      yolov6n.pt
+python deploy/export_onnx.py --weights yolov6s.pt --device 0
+                                       yolov6n.pt
 ```
 
 
diff --git a/tools/export_onnx.py b/deploy/export_onnx.py
similarity index 100%
rename from tools/export_onnx.py
rename to deploy/export_onnx.py
diff --git a/docs/Test_speed.md b/docs/Test_speed.md
index a7b15823..4982186b 100644
--- a/docs/Test_speed.md
+++ b/docs/Test_speed.md
@@ -31,7 +31,7 @@ To  get inference speed with TensorRT in FP16 mode on T4, you can follow the ste
 First, export pytorch model as onnx format using the  following command:
 
 ```shell
-python tools/export_onnx.py --weights yolov6n.pt --device 0 --batch [1 or 32] 
+python deploy/export_onnx.py --weights yolov6n.pt --device 0 --batch [1 or 32] 
 ```
 
 Second,  generate an inference  trt engine and test speed using `trtexec`:
diff --git a/docs/Train_custom_data.md b/docs/Train_custom_data.md
index db487437..f07fce40 100644
--- a/docs/Train_custom_data.md
+++ b/docs/Train_custom_data.md
@@ -125,6 +125,6 @@ python tools/infer.py --weights output_dir/name/weights/best_ckpt.pt --source im
 Export as ONNX Format
 
 ```shell
-python tools/export_onnx.py --weights output_dir/name/weights/best_ckpt.pt --device 0
+python deploy/export_onnx.py --weights output_dir/name/weights/best_ckpt.pt --device 0
 ```