segment-everything 0.1.0__py3-none-any.whl

segment_everything/vendored/object_detection/ultralytics/nn/modules/block.py

@@ -0,0 +1,304 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+"""
+Block modules
+"""
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from .conv import Conv, DWConv, GhostConv, LightConv, RepConv
+from .transformer import TransformerBlock
+
+__all__ = ('DFL', 'HGBlock', 'HGStem', 'SPP', 'SPPF', 'C1', 'C2', 'C3', 'C2f', 'C3x', 'C3TR', 'C3Ghost',
+           'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'RepC3')
+
+
+class DFL(nn.Module):
+    """
+    Integral module of Distribution Focal Loss (DFL).
+    Proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391
+    """
+
+    def __init__(self, c1=16):
+        """Initialize a convolutional layer with a given number of input channels."""
+        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 = c1
+
+    def forward(self, x):
+        """Applies a transformer layer on input tensor 'x' and returns a tensor."""
+        b, c, a = x.shape  # batch, channels, anchors
+        return 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 Proto(nn.Module):
+    """YOLOv8 mask Proto module for segmentation models."""
+
+    def __init__(self, c1, c_=256, c2=32):  # ch_in, number of protos, number of masks
+        super().__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):
+        """Performs a forward pass through layers using an upsampled input image."""
+        return self.cv3(self.cv2(self.upsample(self.cv1(x))))
+
+
+class HGStem(nn.Module):
+    """StemBlock of PPHGNetV2 with 5 convolutions and one maxpool2d.
+    https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
+    """
+
+    def __init__(self, c1, cm, c2):
+        super().__init__()
+        self.stem1 = Conv(c1, cm, 3, 2, act=nn.ReLU())
+        self.stem2a = Conv(cm, cm // 2, 2, 1, 0, act=nn.ReLU())
+        self.stem2b = Conv(cm // 2, cm, 2, 1, 0, act=nn.ReLU())
+        self.stem3 = Conv(cm * 2, cm, 3, 2, act=nn.ReLU())
+        self.stem4 = Conv(cm, c2, 1, 1, act=nn.ReLU())
+        self.pool = nn.MaxPool2d(kernel_size=2, stride=1, padding=0, ceil_mode=True)
+
+    def forward(self, x):
+        """Forward pass of a PPHGNetV2 backbone layer."""
+        x = self.stem1(x)
+        x = F.pad(x, [0, 1, 0, 1])
+        x2 = self.stem2a(x)
+        x2 = F.pad(x2, [0, 1, 0, 1])
+        x2 = self.stem2b(x2)
+        x1 = self.pool(x)
+        x = torch.cat([x1, x2], dim=1)
+        x = self.stem3(x)
+        x = self.stem4(x)
+        return x
+
+
+class HGBlock(nn.Module):
+    """HG_Block of PPHGNetV2 with 2 convolutions and LightConv.
+    https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
+    """
+
+    def __init__(self, c1, cm, c2, k=3, n=6, lightconv=False, shortcut=False, act=nn.ReLU()):
+        super().__init__()
+        block = LightConv if lightconv else Conv
+        self.m = nn.ModuleList(block(c1 if i == 0 else cm, cm, k=k, act=act) for i in range(n))
+        self.sc = Conv(c1 + n * cm, c2 // 2, 1, 1, act=act)  # squeeze conv
+        self.ec = Conv(c2 // 2, c2, 1, 1, act=act)  # excitation conv
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        """Forward pass of a PPHGNetV2 backbone layer."""
+        y = [x]
+        y.extend(m(y[-1]) for m in self.m)
+        y = self.ec(self.sc(torch.cat(y, 1)))
+        return y + x if self.add else y
+
+
+class SPP(nn.Module):
+    """Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729."""
+
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        """Initialize the SPP layer with input/output channels and pooling kernel sizes."""
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.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):
+        """Forward pass of the SPP layer, performing spatial pyramid pooling."""
+        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 Jocher."""
+
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.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):
+        """Forward pass through Ghost Convolution block."""
+        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 C1(nn.Module):
+    """CSP Bottleneck with 1 convolution."""
+
+    def __init__(self, c1, c2, n=1):  # ch_in, ch_out, number
+        super().__init__()
+        self.cv1 = Conv(c1, c2, 1, 1)
+        self.m = nn.Sequential(*(Conv(c2, c2, 3) for _ in range(n)))
+
+    def forward(self, x):
+        """Applies cross-convolutions to input in the C3 module."""
+        y = self.cv1(x)
+        return self.m(y) + y
+
+
+class C2(nn.Module):
+    """CSP Bottleneck with 2 convolutions."""
+
+    def __init__(self, c1, c2, n=1, shortcut=True, 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 * 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):
+        """Forward pass through the CSP bottleneck with 2 convolutions."""
+        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 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):
+        """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))
+
+    def forward_split(self, x):
+        """Forward pass using split() instead of chunk()."""
+        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 C3(nn.Module):
+    """CSP Bottleneck with 3 convolutions."""
+
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.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):
+        """Forward pass through the CSP bottleneck with 2 convolutions."""
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
+
+
+class C3x(C3):
+    """C3 module with cross-convolutions."""
+
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        """Initialize C3TR instance and set default parameters."""
+        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 RepC3(nn.Module):
+    """Rep C3."""
+
+    def __init__(self, c1, c2, n=3, e=1.0):
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c2, 1, 1)
+        self.cv2 = Conv(c1, c2, 1, 1)
+        self.m = nn.Sequential(*[RepConv(c_, c_) for _ in range(n)])
+        self.cv3 = Conv(c_, c2, 1, 1) if c_ != c2 else nn.Identity()
+
+    def forward(self, x):
+        """Forward pass of RT-DETR neck layer."""
+        return self.cv3(self.m(self.cv1(x)) + self.cv2(x))
+
+
+class C3TR(C3):
+    """C3 module with TransformerBlock()."""
+
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        """Initialize C3Ghost module with GhostBottleneck()."""
+        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):
+        """Initialize 'SPP' module with various pooling sizes for spatial pyramid pooling."""
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
+
+
+class GhostBottleneck(nn.Module):
+    """Ghost Bottleneck https://github.com/huawei-noah/ghostnet."""
+
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super().__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(
+            GhostConv(c1, c_, 1, 1),  # pw
+            DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+            GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.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):
+        """Applies skip connection and concatenation to input tensor."""
+        return self.conv(x) + self.shortcut(x)
+
+
+class Bottleneck(nn.Module):
+    """Standard bottleneck."""
+
+    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, k[0], 1)
+        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        """'forward()' applies the YOLOv5 FPN to input data."""
+        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/CrossStagePartialNetworks."""
+
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.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):
+        """Applies a CSP bottleneck with 3 convolutions."""
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))

segment_everything/vendored/object_detection/ultralytics/nn/modules/conv.py

@@ -0,0 +1,297 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+"""
+Convolution modules
+"""
+
+import math
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+__all__ = ('Conv', 'LightConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus', 'GhostConv',
+           'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'RepConv')
+
+
+def autopad(k, p=None, d=1):  # kernel, padding, dilation
+    """Pad to 'same' shape outputs."""
+    if d > 1:
+        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class Conv(nn.Module):
+    """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)."""
+    default_act = nn.SiLU()  # default activation
+
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
+        """Initialize Conv layer with given arguments including activation."""
+        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):
+        """Apply convolution, batch normalization and activation to input tensor."""
+        return self.act(self.bn(self.conv(x)))
+
+    def forward_fuse(self, x):
+        """Perform transposed convolution of 2D data."""
+        return self.act(self.conv(x))
+
+
+class Conv2(Conv):
+    """Simplified RepConv module with Conv fusing."""
+
+    def __init__(self, c1, c2, k=3, s=1, p=None, g=1, d=1, act=True):
+        """Initialize Conv layer with given arguments including activation."""
+        super().__init__(c1, c2, k, s, p, g=g, d=d, act=act)
+        self.cv2 = nn.Conv2d(c1, c2, 1, s, autopad(1, p, d), groups=g, dilation=d, bias=False)  # add 1x1 conv
+
+    def forward(self, x):
+        """Apply convolution, batch normalization and activation to input tensor."""
+        return self.act(self.bn(self.conv(x) + self.cv2(x)))
+
+    def fuse_convs(self):
+        """Fuse parallel convolutions."""
+        w = torch.zeros_like(self.conv.weight.data)
+        i = [x // 2 for x in w.shape[2:]]
+        w[:, :, i[0]:i[0] + 1, i[1]:i[1] + 1] = self.cv2.weight.data.clone()
+        self.conv.weight.data += w
+        self.__delattr__('cv2')
+
+
+class LightConv(nn.Module):
+    """Light convolution with args(ch_in, ch_out, kernel).
+    https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
+    """
+
+    def __init__(self, c1, c2, k=1, act=nn.ReLU()):
+        """Initialize Conv layer with given arguments including activation."""
+        super().__init__()
+        self.conv1 = Conv(c1, c2, 1, act=False)
+        self.conv2 = DWConv(c2, c2, k, act=act)
+
+    def forward(self, x):
+        """Apply 2 convolutions to input tensor."""
+        return self.conv2(self.conv1(x))
+
+
+class DWConv(Conv):
+    """Depth-wise convolution."""
+
+    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)
+
+
+class DWConvTranspose2d(nn.ConvTranspose2d):
+    """Depth-wise transpose convolution."""
+
+    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
+        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
+
+
+class ConvTranspose(nn.Module):
+    """Convolution transpose 2d layer."""
+    default_act = nn.SiLU()  # default activation
+
+    def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
+        """Initialize ConvTranspose2d layer with batch normalization and activation function."""
+        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):
+        """Applies transposed convolutions, batch normalization and activation to input."""
+        return self.act(self.bn(self.conv_transpose(x)))
+
+    def forward_fuse(self, x):
+        """Applies activation and convolution transpose operation to input."""
+        return self.act(self.conv_transpose(x))
+
+
+class Focus(nn.Module):
+    """Focus wh information into c-space."""
+
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__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/ghostnet."""
+
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super().__init__()
+        c_ = c2 // 2  # hidden channels
+        self.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):
+        """Forward propagation through a Ghost Bottleneck layer with skip connection."""
+        y = self.cv1(x)
+        return torch.cat((y, self.cv2(y)), 1)
+
+
+class RepConv(nn.Module):
+    """RepConv is a basic rep-style block, including training and deploy status
+    This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
+    """
+    default_act = nn.SiLU()  # default activation
+
+    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
+        super().__init__()
+        assert k == 3 and p == 1
+        self.g = g
+        self.c1 = c1
+        self.c2 = c2
+        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
+
+        self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None
+        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
+        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)
+
+    def forward_fuse(self, x):
+        """Forward process"""
+        return self.act(self.conv(x))
+
+    def forward(self, x):
+        """Forward process"""
+        id_out = 0 if self.bn is None else self.bn(x)
+        return self.act(self.conv1(x) + self.conv2(x) + id_out)
+
+    def get_equivalent_kernel_bias(self):
+        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
+        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
+        kernelid, biasid = self._fuse_bn_tensor(self.bn)
+        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
+
+    def _avg_to_3x3_tensor(self, avgp):
+        channels = self.c1
+        groups = self.g
+        kernel_size = avgp.kernel_size
+        input_dim = channels // groups
+        k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
+        k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
+        return k
+
+    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
+        if kernel1x1 is None:
+            return 0
+        else:
+            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])
+
+    def _fuse_bn_tensor(self, branch):
+        if branch is None:
+            return 0, 0
+        if isinstance(branch, Conv):
+            kernel = branch.conv.weight
+            running_mean = branch.bn.running_mean
+            running_var = branch.bn.running_var
+            gamma = branch.bn.weight
+            beta = branch.bn.bias
+            eps = branch.bn.eps
+        elif isinstance(branch, nn.BatchNorm2d):
+            if not hasattr(self, 'id_tensor'):
+                input_dim = self.c1 // self.g
+                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
+                for i in range(self.c1):
+                    kernel_value[i, i % input_dim, 1, 1] = 1
+                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
+            kernel = self.id_tensor
+            running_mean = branch.running_mean
+            running_var = branch.running_var
+            gamma = branch.weight
+            beta = branch.bias
+            eps = branch.eps
+        std = (running_var + eps).sqrt()
+        t = (gamma / std).reshape(-1, 1, 1, 1)
+        return kernel * t, beta - running_mean * gamma / std
+
+    def fuse_convs(self):
+        if hasattr(self, 'conv'):
+            return
+        kernel, bias = self.get_equivalent_kernel_bias()
+        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
+                              out_channels=self.conv1.conv.out_channels,
+                              kernel_size=self.conv1.conv.kernel_size,
+                              stride=self.conv1.conv.stride,
+                              padding=self.conv1.conv.padding,
+                              dilation=self.conv1.conv.dilation,
+                              groups=self.conv1.conv.groups,
+                              bias=True).requires_grad_(False)
+        self.conv.weight.data = kernel
+        self.conv.bias.data = bias
+        for para in self.parameters():
+            para.detach_()
+        self.__delattr__('conv1')
+        self.__delattr__('conv2')
+        if hasattr(self, 'nm'):
+            self.__delattr__('nm')
+        if hasattr(self, 'bn'):
+            self.__delattr__('bn')
+        if hasattr(self, 'id_tensor'):
+            self.__delattr__('id_tensor')
+
+
+class ChannelAttention(nn.Module):
+    """Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet."""
+
+    def __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 module."""
+
+    def __init__(self, kernel_size=7):
+        """Initialize Spatial-attention module with kernel size argument."""
+        super().__init__()
+        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
+        padding = 3 if kernel_size == 7 else 1
+        self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
+        self.act = nn.Sigmoid()
+
+    def forward(self, x):
+        """Apply channel and spatial attention on input for feature recalibration."""
+        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 Module."""
+
+    def __init__(self, c1, kernel_size=7):  # ch_in, kernels
+        super().__init__()
+        self.channel_attention = ChannelAttention(c1)
+        self.spatial_attention = SpatialAttention(kernel_size)
+
+    def forward(self, x):
+        """Applies the forward pass through C1 module."""
+        return self.spatial_attention(self.channel_attention(x))
+
+
+class Concat(nn.Module):
+    """Concatenate a list of tensors along dimension."""
+
+    def __init__(self, dimension=1):
+        """Concatenates a list of tensors along a specified dimension."""
+        super().__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        """Forward pass for the YOLOv8 mask Proto module."""
+        return torch.cat(x, self.d)