2025亲测有用 yolov8 pt转onnx转ncnn 部署安卓

 参考文章：pt转onnx转ncnn模型（yolov8部署安卓）_best.pt 转ncnn模型-CSDN博客

Yolov8-Ncnn模型部署Android，实现单一图片识别_yolov8转ncnn-CSDN博客

onnx转化为ncnn这条路径现在已经落后了，更多的是通过pnnx转化为ncnn。

一、pt转onnx

from ultralytics import YOLO# Load a model
model = YOLO(r"E:\StudyData\python\yolov8\yolov8n.pt")  # load a custom trained model# Export the model to NCNN with arguments
success = model.export(format="onnx", simplify= True, opset=12)

修改head和block

class C2f(nn.Module):#省略上面的代码#.....#源代码:# def forward(self, x):#     """Forward pass through C2f layer."""#     y = list(self.cv1(x).chunk(2, 1))#     y.extend(m(y[-1]) for m in self.m)#     return self.cv2(torch.cat(y, 1))#修改为:def forward(self, x):# 全部替换为x = self.cv1(x)x = [x, x[:, self.c:, ...]]x.extend(m(x[-1]) for m in self.m)x.pop(1)return self.cv2(torch.cat(x, 1))

 def __init__(self, nc=80, ch=()):#....省略上面代码#源代码:
# def forward(self, x):
#     """Concatenates and returns predicted bounding boxes and class probabilities."""
#     if self.end2end:
#         return self.forward_end2end(x)
#
#     for i in range(self.nl):
#         x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
#     if self.training:  # Training path
#         return x
#     y = self._inference(x)
#     return y if self.export else (y, x)#修改为:
def forward(self, x):
"""Concatenates and returns predicted bounding boxes and class probabilities."""shape = x[0].shape  # BCHWfor i in range(self.nl):x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)if self.training:return xelif self.dynamic or self.shape != shape:self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))self.shape = shape# 中间部分注释掉，return语句替换为return torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).permute(0, 2, 1)

 

然后执行上述python

如果没找到onnx模块，执行 pip install onnx

得到onnx 

二、对onnx进行简化

pip install onnxsimpython3 -m onnxsim yolov8n.onnx yolov8n-sim.onnx

三、onnx-sim转ncnn

依次执行下面的命令行

sudo apt install build-essential libopencv-dev cmakesudo apt install build-essential git cmake libprotobuf-dev protobuf-compiler libvulkan-dev vulkan-utils libopencv-devgit clone https://github.com/Tencent/ncnn.gitcd ncnngit submodule update --init #暂时不知道什么作用mkdir buildcd buildcmake ..make -j8make installsudo ldconfig  # 刷新

要注意是否成功安装了onnx2ncnn 

找到ncnn/build/tools/onnx文件夹，能找到onnx2ncnn.cpp

把onnx放入文件夹下，执行下面的命令

./onnx2ncnn  my.onnx my.param my.bin

成功得到bin和param文件。