This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
products:sbc:vim4:npu:demos:yolov8n [2024/12/03 02:02] louis |
products:sbc:vim4:npu:demos:yolov8n [2025/06/12 05:39] (current) louis |
||
---|---|---|---|
Line 6: | Line 6: | ||
{{indexmenu_n> | {{indexmenu_n> | ||
+ | |||
+ | ===== Introduction ===== | ||
+ | |||
+ | YOLOv8n is an object detection model. It uses bounding boxes to precisely draw each object in image. | ||
+ | |||
+ | Inference results on VIM4. | ||
+ | |||
+ | {{: | ||
+ | |||
+ | **Inference speed test**: USB camera about **150ms** per frame. | ||
+ | |||
===== Get Source Code ===== | ===== Get Source Code ===== | ||
Line 30: | Line 41: | ||
==== Get Model Conversion Tools ==== | ==== Get Model Conversion Tools ==== | ||
- | Get source [[gl> | + | Get source [[gh> |
- | + | ||
- | ```shell | + | |
- | $ git clone https:// | + | |
- | ``` | + | |
```shell | ```shell | ||
$ git lfs install | $ git lfs install | ||
- | $ git lfs clone https://gitlab.com/ | + | $ git lfs clone https://github.com/ |
$ cd vim4_npu_sdk | $ cd vim4_npu_sdk | ||
$ ls | $ ls | ||
Line 49: | Line 56: | ||
<WRAP important> | <WRAP important> | ||
- | If your kernel is older than 241129, please use version before tag ddk-3.4.7.7. | + | If your kernel is older than 241129, please use branch npu-ddk-1.7.5.5. |
</ | </ | ||
Line 81: | Line 88: | ||
+ cls = self.cv3[i](x[i]).contiguous() | + cls = self.cv3[i](x[i]).contiguous() | ||
+ results.append(torch.cat([cls, | + results.append(torch.cat([cls, | ||
- | + # results.append(torch.cat([cls, | ||
+ return tuple(results) | + return tuple(results) | ||
+ | + | ||
Line 179: | Line 185: | ||
$ ./yolov8n -m ../ | $ ./yolov8n -m ../ | ||
``` | ``` | ||
- | |||
- | {{: | ||
=== Camera input demo === | === Camera input demo === | ||
Line 195: | Line 199: | ||
# Run | # Run | ||
- | $ ./ | + | $ ./ |
``` | ``` | ||