Differences

This shows you the differences between two versions of the page.

--- products:sbc:edge2:npu:demos:yolov8n [2023/09/19 22:42]
louis
+++ products:sbc:edge2:npu:demos:yolov8n [2024/07/03 21:44] (current)
louis
@@ Line 13: / Line 13: @@
 ```
-Refer ''README.md'' to train a YOLOv8n model.
+Refer ''README.md'' to train a YOLOv8n model. My version ''torch==1.10.1'' and ''ultralytics==8.0.86''.
 ===== Convert Model =====
@@ Line 61: / Line 61: @@
 After training model, modify ''ultralytics/ultralytics/nn/modules/head.py'' as follows.
-```diff
+```diff head.py
 diff --git a/ultralytics/nn/modules/head.py b/ultralytics/nn/modules/head.py
 index 0b02eb3..0a6e43a 100644
@@ Line 90: / Line 90: @@
 +
 ```
+<WRAP important>
+If you pip-installed ultralytics package, you should modify in package.
+</WRAP>
 Create a python file written as follows to export **onnx** model.
@@ Line 98: / Line 102: @@
 results = model.export(format="onnx")
 ```
+<WRAP important>
+Use [[https://netron.app/ | Netron]] to check your model output like this. If not, please check your ''head.py''.
+{{:products:sbc:edge2:npu:demos:yolov8n-edge2-output.png?600|}}
+</WRAP>
 Enter ''rknn-toolkit2/examples/onnx/yolov5'' and modify ''test.py'' as follows.
@@ Line 145: / Line 155: @@
 ==== Get source code ====
-Clone the source code form our [[gh>khadas/edge2-npu]].
+Clone the source code from our [[gh>khadas/edge2-npu]].
 ```shell

Khadas Docs