Android设备运行yolov8

放假这几天搞了一个基于uniapp+rk3588实现了一版yolo检测

这个是基于前端调用后端api来实现，感觉还可以，但是需要有网络才能进行图像检测，网络不稳定就会出现等待时间会比较久的问题，然后有做了一个在做了一个Android版本的图像检测，我也是参考别人的实现来弄了。
记录一下大概步骤：
1.先安装Android Studio工具
2.下载检测代码yolov8安卓端识别代码
3.配置项目环境，项目下载下来只要环境配置好就可以运行，运行不起来不要怀疑是代码问题，大概下图中的都配置好没报错就可以连接手机，开始真机运行了



4.项目中默认运行项目中自带模型，如果想换其他模型，可以自己训练后转换进行替换
4.1替换默认模型大概步骤
先去拉取yolov8的训练代码 目前我使用yolov8-8.0.50版本，注意训练和导出onnx模型代码要分开，也就是说可以分成两套，下载好yolov8-8.0.50版本代码多复制一份出来，修改其中一套出来用于模型转换（pt转onnx）
具体修改：替换ultralytics-8.0.50\ultralytics-8.0.50\ultralytics\nn\modules.py中的内容，可以直接复制粘贴替换，替换完这个项目用于pt转onnx
转换还需要安装 onnx-simplifier

    pip install   onnx-simplifier  #用于简化onnx模型

# Ultralytics YOLO 🚀, GPL-3.0 license
"""
Common modules
"""import mathimport torch
import torch.nn as nnfrom ultralytics.yolo.utils.tal import dist2bbox, make_anchorsdef autopad(k, p=None, d=1):  # kernel, padding, dilation# Pad to 'same' shape outputsif d > 1:k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-sizeif p is None:p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-padreturn pclass Conv(nn.Module):# Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)default_act = nn.SiLU()  # default activationdef __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):super().__init__()self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)self.bn = nn.BatchNorm2d(c2)self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()def forward(self, x):return self.act(self.bn(self.conv(x)))def forward_fuse(self, x):return self.act(self.conv(x))class DWConv(Conv):# Depth-wise convolutiondef __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activationsuper().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)class DWConvTranspose2d(nn.ConvTranspose2d):# Depth-wise transpose convolutiondef __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_outsuper().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))class ConvTranspose(nn.Module):# Convolution transpose 2d layerdefault_act = nn.SiLU()  # default activationdef __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):super().__init__()self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn)self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity()self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()def forward(self, x):return self.act(self.bn(self.conv_transpose(x)))def forward_fuse(self, x):return self.act(self.conv_transpose(x))class DFL(nn.Module):# Integral module of Distribution Focal Loss (DFL) proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391def __init__(self, c1=16):super().__init__()self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)x = torch.arange(c1, dtype=torch.float)self.conv.weight.data[:] = nn.Parameter(x.view(1, c1, 1, 1))self.c1 = c1def forward(self, x):b, c, a = x.shape  # batch, channels, anchorsreturn self.conv(x.view(b, 4, self.c1, a).transpose(2, 1).softmax(1)).view(b, 4, a)# return self.conv(x.view(b, self.c1, 4, a).softmax(1)).view(b, 4, a)class TransformerLayer(nn.Module):# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)def __init__(self, c, num_heads):super().__init__()self.q = nn.Linear(c, c, bias=False)self.k = nn.Linear(c, c, bias=False)self.v = nn.Linear(c, c, bias=False)self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)self.fc1 = nn.Linear(c, c, bias=False)self.fc2 = nn.Linear(c, c, bias=False)def forward(self, x):x = self.ma(self.q(x), self.k(x), self.v(x))[0] + xx = self.fc2(self.fc1(x)) + xreturn xclass TransformerBlock(nn.Module):# Vision Transformer https://arxiv.org/abs/2010.11929def __init__(self, c1, c2, num_heads, num_layers):super().__init__()self.conv = Noneif c1 != c2:self.conv = Conv(c1, c2)self.linear = nn.Linear(c2, c2)  # learnable position embeddingself.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))self.c2 = c2def forward(self, x):if self.conv is not None:x = self.conv(x)b, _, w, h = x.shapep = x.flatten(2).permute(2, 0, 1)return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)class Bottleneck(nn.Module):# Standard bottleneckdef __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expandsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, k[0], 1)self.cv2 = Conv(c_, c2, k[1], 1, g=g)self.add = shortcut and c1 == c2def forward(self, x):return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))class BottleneckCSP(nn.Module):# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworksdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)self.cv4 = Conv(2 * c_, c2, 1, 1)self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)self.act = nn.SiLU()self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))def forward(self, x):y1 = self.cv3(self.m(self.cv1(x)))y2 = self.cv2(x)return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))class C3(nn.Module):# CSP Bottleneck with 3 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c1, c_, 1, 1)self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))def forward(self, x):return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))class C2(nn.Module):# CSP Bottleneck with 2 convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()self.c = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, 2 * self.c, 1, 1)self.cv2 = Conv(2 * self.c, c2, 1)  # optional act=FReLU(c2)# self.attention = ChannelAttention(2 * self.c)  # or SpatialAttention()self.m = nn.Sequential(*(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n)))def forward(self, x):a, b = self.cv1(x).chunk(2, 1)return self.cv2(torch.cat((self.m(a), b), 1))class C2f(nn.Module):# CSP Bottleneck with 2 convolutionsdef __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()self.c = int(c2 * e)  # hidden channelsself.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):# 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))print('forward C2f')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):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))class ChannelAttention(nn.Module):# Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdetdef __init__(self, channels: int) -> None:super().__init__()self.pool = nn.AdaptiveAvgPool2d(1)self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)self.act = nn.Sigmoid()def forward(self, x: torch.Tensor) -> torch.Tensor:return x * self.act(self.fc(self.pool(x)))class SpatialAttention(nn.Module):# Spatial-attention moduledef __init__(self, kernel_size=7):super().__init__()assert kernel_size in (3, 7), 'kernel size must be 3 or 7'padding = 3 if kernel_size == 7 else 1self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)self.act = nn.Sigmoid()def forward(self, x):return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))class CBAM(nn.Module):# Convolutional Block Attention Moduledef __init__(self, c1, kernel_size=7):  # ch_in, kernelssuper().__init__()self.channel_attention = ChannelAttention(c1)self.spatial_attention = SpatialAttention(kernel_size)def forward(self, x):return self.spatial_attention(self.channel_attention(x))class C1(nn.Module):# CSP Bottleneck with 1 convolutiondef __init__(self, c1, c2, n=1):  # ch_in, ch_out, numbersuper().__init__()self.cv1 = Conv(c1, c2, 1, 1)self.m = nn.Sequential(*(Conv(c2, c2, 3) for _ in range(n)))def forward(self, x):y = self.cv1(x)return self.m(y) + yclass C3x(C3):# C3 module with cross-convolutionsdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__(c1, c2, n, shortcut, g, e)self.c_ = int(c2 * e)self.m = nn.Sequential(*(Bottleneck(self.c_, self.c_, shortcut, g, k=((1, 3), (3, 1)), e=1) for _ in range(n)))class C3TR(C3):# C3 module with TransformerBlock()def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__(c1, c2, n, shortcut, g, e)c_ = int(c2 * e)self.m = TransformerBlock(c_, c_, 4, n)class C3Ghost(C3):# C3 module with GhostBottleneck()def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__(c1, c2, n, shortcut, g, e)c_ = int(c2 * e)  # hidden channelsself.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))class SPP(nn.Module):# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729def __init__(self, c1, c2, k=(5, 9, 13)):super().__init__()c_ = c1 // 2  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])def forward(self, x):x = self.cv1(x)return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))class SPPF(nn.Module):# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocherdef __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))super().__init__()c_ = c1 // 2  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c_ * 4, c2, 1, 1)self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)def forward(self, x):x = self.cv1(x)y1 = self.m(x)y2 = self.m(y1)return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))class Focus(nn.Module):# Focus wh information into c-spacedef __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groupssuper().__init__()self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)# self.contract = Contract(gain=2)def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))# return self.conv(self.contract(x))class GhostConv(nn.Module):# Ghost Convolution https://github.com/huawei-noah/ghostnetdef __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groupssuper().__init__()c_ = c2 // 2  # hidden channelsself.cv1 = Conv(c1, c_, k, s, None, g, act=act)self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)def forward(self, x):y = self.cv1(x)return torch.cat((y, self.cv2(y)), 1)class GhostBottleneck(nn.Module):# Ghost Bottleneck https://github.com/huawei-noah/ghostnetdef __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stridesuper().__init__()c_ = c2 // 2self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pwDWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dwGhostConv(c_, c2, 1, 1, act=False))  # pw-linearself.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1,act=False)) if s == 2 else nn.Identity()def forward(self, x):return self.conv(x) + self.shortcut(x)class Concat(nn.Module):# Concatenate a list of tensors along dimensiondef __init__(self, dimension=1):super().__init__()self.d = dimensiondef forward(self, x):return torch.cat(x, self.d)class Proto(nn.Module):# YOLOv8 mask Proto module for segmentation modelsdef __init__(self, c1, c_=256, c2=32):  # ch_in, number of protos, number of maskssuper().__init__()self.cv1 = Conv(c1, c_, k=3)self.upsample = nn.ConvTranspose2d(c_, c_, 2, 2, 0, bias=True)  # nn.Upsample(scale_factor=2, mode='nearest')self.cv2 = Conv(c_, c_, k=3)self.cv3 = Conv(c_, c2)def forward(self, x):return self.cv3(self.cv2(self.upsample(self.cv1(x))))class Ensemble(nn.ModuleList):# Ensemble of modelsdef __init__(self):super().__init__()def forward(self, x, augment=False, profile=False, visualize=False):y = [module(x, augment, profile, visualize)[0] for module in self]# y = torch.stack(y).max(0)[0]  # max ensemble# y = torch.stack(y).mean(0)  # mean ensembley = torch.cat(y, 1)  # nms ensemblereturn y, None  # inference, train output# heads
class Detect(nn.Module):# YOLOv8 Detect head for detection modelsdynamic = False  # force grid reconstructionexport = False  # export modeshape = Noneanchors = torch.empty(0)  # initstrides = torch.empty(0)  # initdef __init__(self, nc=80, ch=()):  # detection layersuper().__init__()self.nc = nc  # number of classesself.nl = len(ch)  # number of detection layersself.reg_max = 16  # DFL channels (ch[0] // 16 to scale 4/8/12/16/20 for n/s/m/l/x)self.no = nc + self.reg_max * 4  # number of outputs per anchorself.stride = torch.zeros(self.nl)  # strides computed during buildc2, c3 = max((16, ch[0] // 4, self.reg_max * 4)), max(ch[0], self.nc)  # channelsself.cv2 = nn.ModuleList(nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch)self.cv3 = nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()def forward(self, x):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# if self.export and self.format == 'edgetpu':  # FlexSplitV ops issue#     x_cat = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2)#     box = x_cat[:, :self.reg_max * 4]#     cls = x_cat[:, self.reg_max * 4:]# else:#     box, cls = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).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)print('forward Detect')pred = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).permute(0, 2, 1)return preddef bias_init(self):# Initialize Detect() biases, WARNING: requires stride availabilitym = self  # self.model[-1]  # Detect() module# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1# ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # nominal class frequencyfor a, b, s in zip(m.cv2, m.cv3, m.stride):  # froma[-1].bias.data[:] = 1.0  # boxb[-1].bias.data[:m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (.01 objects, 80 classes, 640 img)class Segment(Detect):# YOLOv8 Segment head for segmentation modelsdef __init__(self, nc=80, nm=32, npr=256, ch=()):super().__init__(nc, ch)self.nm = nm  # number of masksself.npr = npr  # number of protosself.proto = Proto(ch[0], self.npr, self.nm)  # protosself.detect = Detect.forwardc4 = max(ch[0] // 4, self.nm)self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nm, 1)) for x in ch)def forward(self, x):p = self.proto(x[0])  # mask protosbs = p.shape[0]  # batch sizemc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)], 2)  # mask coefficientsx = self.detect(self, x)if self.training:return x, mc, preturn (torch.cat([x, mc], 1), p) if self.export else (torch.cat([x[0], mc], 1), (x[1], mc, p))class Classify(nn.Module):# YOLOv8 classification head, i.e. x(b,c1,20,20) to x(b,c2)def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groupssuper().__init__()c_ = 1280  # efficientnet_b0 sizeself.conv = Conv(c1, c_, k, s, autopad(k, p), g)self.pool = nn.AdaptiveAvgPool2d(1)  # to x(b,c_,1,1)self.drop = nn.Dropout(p=0.0, inplace=True)self.linear = nn.Linear(c_, c2)  # to x(b,c2)def forward(self, x):if isinstance(x, list):x = torch.cat(x, 1)x = self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))return x if self.training else x.softmax(1)

5.onnx转ncnn
去官网下载ncnn转换工具

下载完成后打开进入到ncnn-20241226-windows-vs2019\ncnn-20241226-windows-vs2019\x86\bin下面

打开cmd终端执行下面命令 后面的onnx填自己转换的模型
onnx2ncnn.exe yolo.onnx

转换完后会产生两个 bin结尾和param结尾的文件
打开param文件修改最后一行，把output0改成output，这个里面的内容不一定要完全和ncnn-android-yolov8项目中的模型内容一样，刚开始我产生了误区是转换出来必须和项目中的模型内容一样，其实不一样也可以，修改完后就可以拿去替换项目中的模型了

注意：项目中的模型默认是80类别的 如果替换会自己训练的模型一定要对应修改，类别数量
可以下载我上传的android-yolov8检测资源文件，已经测试过没问题