基于 NCNN, 实现 yolov8

在这里插入图片描述

记录下基于 ncnn 实现 yolov8 的全部过程

修改 ultralytics/nn/modules.py class Detect forward 和 class C2f forward

class Detect(nn.Module):
...
    def forward(self, x):
        shape = x[0].shape  # BCHW
        for i in range(self.nl):
            x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
        if self.training:
            return x
        elif 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

        # x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)
        # if self.export and self.format in ('saved_model', 'pb', 'tflite', 'edgetpu', 'tfjs'):  # avoid TF FlexSplitV ops
        #     box = x_cat[:, :self.reg_max * 4]
        #     cls = x_cat[:, self.reg_max * 4:]
        # else:
        #     box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
        # dbox = dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywh=True, dim=1) * self.strides
        # y = torch.cat((dbox, cls.sigmoid()), 1)
        # return y if self.export else (y, x)
        
        pred = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).permute(0, 2, 1)
        return pred


class C2f(nn.Module):
    export = False  # export mode
    # CSP Bottleneck with 2 convolutions
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        if not self.export:
            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))
        
        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 forward_split(self, x):
        if not self.export:
            print("------------> c2f forward_split:")
            y = list(self.cv1(x).split((self.c, self.c), 1))
            y.extend(m(y[-1]) for m in self.m)
            return self.cv2(torch.cat(y, 1))
        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))

生成 onnx，创建 export.py

from ultralytics import YOLO
# load yolov8 segment model
model = YOLO("yolov8n.pt")
# Use the model
success = model.export(format="onnx", opset=13, simplify=True)

导出 ncnn 模型

./onnx2ncnn models/yolov8n.onnx models/yolov8n.param models/yolov8n.bin
./ncnnoptimize models/yolov8n.param models/yolov8n.bin models/yolov8n-opt.param models/yolov8n-opt.bin 65536

测试参考 https://github.com/FeiGeChuanShu/ncnn-android-yolov8

在这里插入图片描述

Q&A

Shape not supported yet!
修改 modules.py class detect 和 class c2f

./ncnnoptimize models/yolov8n.param models/yolov8n.bin models/yolov8n-opt.param models/yolov8n-opt.bin 65536 报错
尝试通过网上在线方式转换 fp16，成功了。但使用ncnn 加载模型总是报错。在网上一顿找，各位大佬都验证好用，到我这就怎么转都报错，很是苦逼。后来索性换了个yolov8版本，结果好使了，麻蛋的。

# 其实警告已经表示 该版本不支持 onnx exported.  没注意，以为无伤大雅了。
Results saved to /home/qh/workspace/train/ultralytics-v8
Predict:         yolo task=detect mode=predict model=yolov8n.onnx -WARNING ⚠️ not yet supported for YOLOv8 exported models
Validate:        yolo task=detect mode=val model=yolov8n.onnx -WARNING ⚠️ not yet supported for YOLOv8 exported models

基于 NCNN, 实现 yolov8

Q&A

参考

悦读