From ec191e1dc0e77fefb1c633c6c5c363fe288a1f99 Mon Sep 17 00:00:00 2001
From: Denisdiba <80591082+THORRDE@users.noreply.github.com>
Date: Tue, 27 May 2025 14:00:33 +0200
Subject: [PATCH] Update How_to_deploy_yolov8_yolov5_object_detection.md

"yolo export" command not found fix
---
 .../tuto/How_to_deploy_yolov8_yolov5_object_detection.md    | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/object_detection/deployment/doc/tuto/How_to_deploy_yolov8_yolov5_object_detection.md b/object_detection/deployment/doc/tuto/How_to_deploy_yolov8_yolov5_object_detection.md
index 4c3b3f5cd..4ed6818dc 100644
--- a/object_detection/deployment/doc/tuto/How_to_deploy_yolov8_yolov5_object_detection.md
+++ b/object_detection/deployment/doc/tuto/How_to_deploy_yolov8_yolov5_object_detection.md
@@ -54,7 +54,11 @@ Please refer to [https://github.com/ultralytics/ultralytics](https://github.com/
 To export the model as int8 tflite, let's take the default example of a model trained on COCO dataset using Ultralytics CLI:
 
 ```
-	yolo export model=yolov8n.pt format=tflite imgsz=256  int8=True
+model.export(
+    format="tflite",
+    imgsz=256,
+    int8=True
+)
 ```
 
 Where yolov8n.pt is the trained weights, the output format is specified as tflite, int8=True means the model will be quantized using 8-bits signed for the weights and the activations.