We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
导出模型时使用yolo cli
yolo export model=cc_yolo11n.pt format=ncnn
看到 #5721 说yolov11可以直接使用v8的例程,因此直接编译了examples/yolov8.cpp 将生成的cc_yolo11n_ncnn_model下的model.ncnn.param以及model.ncnn.bin分别改名为yolov8.param和yolov8.bin。编译yolov8.cpp后运行./yolov8 test.png 乱框。将实例代码yolov8.cpp中的class_names[]改为自行训练的类型名称和数量也是类似的结果。
examples/yolov8.cpp
cc_yolo11n_ncnn_model
model.ncnn.param
model.ncnn.bin
yolov8.param
yolov8.bin
yolov8.cpp
./yolov8 test.png
class_names[]
测试了ultralytics的官方coco数据集预训练模型yolo11n.pt,使用同样的方法导出为ncnn格式,并无此问题。可以正常输出检测结果。
yolo11n.pt
求助排查思路,是需要更改.param文件还是实例yolov8.cpp代码以适应自训练的模型么?
.param
自训练模型为fp32精度。基于yolo11n,使用yolo cli命令行训练 以下是我的模型的.param文件 yolov8n.param.txt
The content you are editing has changed. Please copy your edits and refresh the page.
The text was updated successfully, but these errors were encountered:
使用ultralytics的yolo cli进行自训练的这个ncnn模型的推理没有问题。但使用examples/yolov8.cpp中的代码便无法推理。
yolo predict model='cc_yolo11n_ncnn_model' source=color_circle_test3.mp4 show=True
Sorry, something went wrong.
No branches or pull requests
detail | 详细描述 | 詳細な説明
导出模型时使用yolo cli
yolo export model=cc_yolo11n.pt format=ncnn
看到 #5721 说yolov11可以直接使用v8的例程,因此直接编译了
examples/yolov8.cpp
将生成的
cc_yolo11n_ncnn_model
下的model.ncnn.param
以及model.ncnn.bin
分别改名为yolov8.param
和yolov8.bin
。编译yolov8.cpp
后运行./yolov8 test.png
乱框。将实例代码yolov8.cpp
中的class_names[]
改为自行训练的类型名称和数量也是类似的结果。测试了ultralytics的官方coco数据集预训练模型
yolo11n.pt
,使用同样的方法导出为ncnn格式,并无此问题。可以正常输出检测结果。求助排查思路,是需要更改
.param
文件还是实例yolov8.cpp
代码以适应自训练的模型么?自训练模型为fp32精度。基于yolo11n,使用yolo cli命令行训练
以下是我的模型的
.param
文件yolov8n.param.txt
Tasks
The text was updated successfully, but these errors were encountered: