yolov5的问题总结

yolo.py

• 一般前向推理时常用的还是forward_once就可以
• Detect中的stride可以理解为网格的大小，例如取输入为[4,3,640,640]则根据anchors的大小计算出stride为[8,16,32],则输出为[4,3,80,80,85],[4,3,40,40,85],[4,3,20,20,85]。80*8=640,40*16=640,20*32=640。
• Detect模块里面的stride是在Model里面计算的，即这一部分：

if isinstance(m, Detect):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
            m.anchors /= m.stride.view(-1, 1, 1)
            check_anchor_order(m)
            self.stride = m.stride
            self._initialize_biases()  # only run once

其中s=256是固定的，所以不管输入或者锚框如何变化，算出来的m.sttride都是8,16,32,所以输入的图像大小最好是32的倍数，一般为640或608

class Detect(nn.Module):
    stride = None  # strides computed during build
    onnx_dynamic = False  # ONNX export parameter

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.inplace = inplace  # use in-place ops (e.g. slice assignment)
        print(f'self.stride in Detect:{self.stride}')

    def forward(self, x):
        z = []  # inference output
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                y = x[i].sigmoid()
                if self.inplace:
                    y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, y[..., 4:]), -1)
                z.append(y.view(bs, -1, self.no))

        return x if self.training else (torch.cat(z, 1), x)

    def _make_grid(self, nx=20, ny=20, i=0):
        d = self.anchors[i].device
        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
        else:
            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
        grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
        anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
            .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
        return grid, anchor_grid


class Model(nn.Module):
    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
        super().__init__()
        if isinstance(cfg, dict):
            self.yaml = cfg  # model dict
        else:  # is *.yaml
            import yaml  # for torch hub
            self.yaml_file = Path(cfg).name
            with open(cfg, encoding='ascii', errors='ignore') as f:
                self.yaml = yaml.safe_load(f)  # model dict

        # Define model
        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
        if nc and nc != self.yaml['nc']:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml['nc'] = nc  # override yaml value
        if anchors:
            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
            self.yaml['anchors'] = round(anchors)  # override yaml value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
        self.inplace = self.yaml.get('inplace', True)

        # Build strides, anchors
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
            m.anchors /= m.stride.view(-1, 1, 1)
            print(f'anchors:{m.anchors.shape}   m.stirde.shape:{m.stride.view(-1,1,1).shape}')
            check_anchor_order(m)
            self.stride = m.stride
            self._initialize_biases()  # only run once
            # print(f'in init :Detect.stride :{m.stride}, inpale:{m.inplace}, anchors:{m.anchors}')  

        # Init weights, biases
        initialize_weights(self)
        # self.info()
        LOGGER.info('')

    def forward(self, x, augment=False, profile=False, visualize=False):
        if augment:
            return self._forward_augment(x)  # augmented inference, None
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_augment(self, x):
        img_size = x.shape[-2:]  # height, width
        s = [1, 0.83, 0.67]  # scales
        f = [None, 3, None]  # flips (2-ud, 3-lr)
        y = []  # outputs
        for si, fi in zip(s, f):
            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
            yi = self._forward_once(xi)[0]  # forward
            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
            yi = self._descale_pred(yi, fi, si, img_size)
            y.append(yi)
        y = self._clip_augmented(y)  # clip augmented tails
        return torch.cat(y, 1), None  # augmented inference, train

    def _forward_once(self, x, profile=False, visualize=False):
        y, dt = [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
        return x

    def _descale_pred(self, p, flips, scale, img_size):
        # de-scale predictions following augmented inference (inverse operation)
        if self.inplace:
            p[..., :4] /= scale  # de-scale
            if flips == 2:
                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
            elif flips == 3:
                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
        else:
            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
            if flips == 2:
                y = img_size[0] - y  # de-flip ud
            elif flips == 3:
                x = img_size[1] - x  # de-flip lr
            p = torch.cat((x, y, wh, p[..., 4:]), -1)
        return p

    def _clip_augmented(self, y):
        # Clip YOLOv5 augmented inference tails
        nl = self.model[-1].nl  # number of detection layers (P3-P5)
        g = sum(4 ** x for x in range(nl))  # grid points
        e = 1  # exclude layer count
        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
        y[0] = y[0][:, :-i]  # large
        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
        y[-1] = y[-1][:, i:]  # small
        return y

    def _profile_one_layer(self, m, x, dt):
        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
        t = time_sync()
        for _ in range(10):
            m(x.copy() if c else x)
        dt.append((time_sync() - t) * 100)
        if m == self.model[0]:
            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
        if c:
            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")

    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
        # https://arxiv.org/abs/1708.02002 section 3.3
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
        m = self.model[-1]  # Detect() module
        for mi, s in zip(m.m, m.stride):  # from
            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # cls
            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)

    def _print_biases(self):
        m = self.model[-1]  # Detect() module
        for mi in m.m:  # from
            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
            LOGGER.info(
                ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))

    # def _print_weights(self):
    #     for m in self.model.modules():
    #         if type(m) is Bottleneck:
    #             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')
        for m in self.model.modules():
            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
        self.info()
        return self

    def info(self, verbose=False, img_size=640):  # print model information
        model_info(self, verbose, img_size)

    def _apply(self, fn):
        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self = super()._apply(fn)
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):
            m.stride = fn(m.stride)
            m.grid = list(map(fn, m.grid))
            if isinstance(m.anchor_grid, list):
                m.anchor_grid = list(map(fn, m.anchor_grid))
        return self