ultralytics 8.2.36__py3-none-any.whl → 8.2.38__py3-none-any.whl

tests/test_python.py

@@ -577,3 +577,12 @@ def test_yolo_world():
         close_mosaic=1,
         trainer=WorldTrainerFromScratch,
     )
+
+
+def test_yolov10():
+    """A simple test for yolov10 for now."""
+    model = YOLO("yolov10n.yaml")
+    # train/val/predict
+    model.train(data="coco8.yaml", epochs=1, imgsz=32, close_mosaic=1, cache="disk")
+    model.val(data="coco8.yaml", imgsz=32)
+    model(SOURCE)

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.36"
+__version__ = "8.2.38"
 
 import os
 

ultralytics/cfg/models/v10/yolov10b.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  b: [0.67, 1.00, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10l.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10m.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  m: [0.67, 0.75, 768]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10n.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10s.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  s: [0.33, 0.50, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10x.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  x: [1.00, 1.25, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2fCIB, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/data/loaders.py

@@ -362,7 +362,7 @@ class LoadImagesAndVideos:
                 self.mode = "image"
                 im0 = cv2.imread(path)  # BGR
                 if im0 is None:
-                    raise FileNotFoundError(f"Image Not Found {path}")
+                    raise FileNotFoundError(f"Image Read Error {path}")
                 paths.append(path)
                 imgs.append(im0)
                 info.append(f"image {self.count + 1}/{self.nf} {path}: ")

ultralytics/engine/exporter.py

@@ -920,6 +920,7 @@ class Exporter:
     @try_export
     def export_tflite(self, keras_model, nms, agnostic_nms, prefix=colorstr("TensorFlow Lite:")):
         """YOLOv8 TensorFlow Lite export."""
+        # BUG https://github.com/ultralytics/ultralytics/issues/13436
         import tensorflow as tf  # noqa
 
         LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...")

ultralytics/nn/modules/__init__.py

@@ -22,18 +22,22 @@ from .block import (
     C2,
     C3,
     C3TR,
+    CIB,
     DFL,
     ELAN1,
+    PSA,
     SPP,
     SPPELAN,
     SPPF,
     AConv,
     ADown,
+    Attention,
     BNContrastiveHead,
     Bottleneck,
     BottleneckCSP,
     C2f,
     C2fAttn,
+    C2fCIB,
     C3Ghost,
     C3x,
     CBFuse,
@@ -46,7 +50,9 @@ from .block import (
     Proto,
     RepC3,
     RepNCSPELAN4,
+    RepVGGDW,
     ResNetLayer,
+    SCDown,
 )
 from .conv import (
     CBAM,
@@ -63,7 +69,7 @@ from .conv import (
     RepConv,
     SpatialAttention,
 )
-from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect
+from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect, v10Detect
 from .transformer import (
     AIFI,
     MLP,
@@ -137,4 +143,10 @@ __all__ = (
     "CBLinear",
     "AConv",
     "ELAN1",
+    "RepVGGDW",
+    "CIB",
+    "C2fCIB",
+    "Attention",
+    "PSA",
+    "SCDown",
 )

ultralytics/nn/modules/block.py

@@ -5,6 +5,8 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+from ultralytics.utils.torch_utils import fuse_conv_and_bn
+
 from .conv import Conv, DWConv, GhostConv, LightConv, RepConv, autopad
 from .transformer import TransformerBlock
 
@@ -39,6 +41,12 @@ __all__ = (
     "CBFuse",
     "CBLinear",
     "Silence",
+    "RepVGGDW",
+    "CIB",
+    "C2fCIB",
+    "Attention",
+    "PSA",
+    "SCDown",
 )
 
 
@@ -672,18 +680,6 @@ class SPPELAN(nn.Module):
         return self.cv5(torch.cat(y, 1))
 
 
-class Silence(nn.Module):
-    """Silence."""
-
-    def __init__(self):
-        """Initializes the Silence module."""
-        super(Silence, self).__init__()
-
-    def forward(self, x):
-        """Forward pass through Silence layer."""
-        return x
-
-
 class CBLinear(nn.Module):
     """CBLinear."""
 
@@ -711,3 +707,251 @@ class CBFuse(nn.Module):
         target_size = xs[-1].shape[2:]
         res = [F.interpolate(x[self.idx[i]], size=target_size, mode="nearest") for i, x in enumerate(xs[:-1])]
         return torch.sum(torch.stack(res + xs[-1:]), dim=0)
+
+
+class RepVGGDW(torch.nn.Module):
+    """RepVGGDW is a class that represents a depth wise separable convolutional block in RepVGG architecture."""
+
+    def __init__(self, ed) -> None:
+        super().__init__()
+        self.conv = Conv(ed, ed, 7, 1, 3, g=ed, act=False)
+        self.conv1 = Conv(ed, ed, 3, 1, 1, g=ed, act=False)
+        self.dim = ed
+        self.act = nn.SiLU()
+
+    def forward(self, x):
+        """
+        Performs a forward pass of the RepVGGDW block.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            (torch.Tensor): Output tensor after applying the depth wise separable convolution.
+        """
+        return self.act(self.conv(x) + self.conv1(x))
+
+    def forward_fuse(self, x):
+        """
+        Performs a forward pass of the RepVGGDW block without fusing the convolutions.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            (torch.Tensor): Output tensor after applying the depth wise separable convolution.
+        """
+        return self.act(self.conv(x))
+
+    @torch.no_grad()
+    def fuse(self):
+        """
+        Fuses the convolutional layers in the RepVGGDW block.
+
+        This method fuses the convolutional layers and updates the weights and biases accordingly.
+        """
+        conv = fuse_conv_and_bn(self.conv.conv, self.conv.bn)
+        conv1 = fuse_conv_and_bn(self.conv1.conv, self.conv1.bn)
+
+        conv_w = conv.weight
+        conv_b = conv.bias
+        conv1_w = conv1.weight
+        conv1_b = conv1.bias
+
+        conv1_w = torch.nn.functional.pad(conv1_w, [2, 2, 2, 2])
+
+        final_conv_w = conv_w + conv1_w
+        final_conv_b = conv_b + conv1_b
+
+        conv.weight.data.copy_(final_conv_w)
+        conv.bias.data.copy_(final_conv_b)
+
+        self.conv = conv
+        del self.conv1
+
+
+class CIB(nn.Module):
+    """
+    Conditional Identity Block (CIB) module.
+
+    Args:
+        c1 (int): Number of input channels.
+        c2 (int): Number of output channels.
+        shortcut (bool, optional): Whether to add a shortcut connection. Defaults to True.
+        e (float, optional): Scaling factor for the hidden channels. Defaults to 0.5.
+        lk (bool, optional): Whether to use RepVGGDW for the third convolutional layer. Defaults to False.
+    """
+
+    def __init__(self, c1, c2, shortcut=True, e=0.5, lk=False):
+        """Initializes the custom model with optional shortcut, scaling factor, and RepVGGDW layer."""
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = nn.Sequential(
+            Conv(c1, c1, 3, g=c1),
+            Conv(c1, 2 * c_, 1),
+            Conv(2 * c_, 2 * c_, 3, g=2 * c_) if not lk else RepVGGDW(2 * c_),
+            Conv(2 * c_, c2, 1),
+            Conv(c2, c2, 3, g=c2),
+        )
+
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        """
+        Forward pass of the CIB module.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            (torch.Tensor): Output tensor.
+        """
+        return x + self.cv1(x) if self.add else self.cv1(x)
+
+
+class C2fCIB(C2f):
+    """
+    C2fCIB class represents a convolutional block with C2f and CIB modules.
+
+    Args:
+        c1 (int): Number of input channels.
+        c2 (int): Number of output channels.
+        n (int, optional): Number of CIB modules to stack. Defaults to 1.
+        shortcut (bool, optional): Whether to use shortcut connection. Defaults to False.
+        lk (bool, optional): Whether to use local key connection. Defaults to False.
+        g (int, optional): Number of groups for grouped convolution. Defaults to 1.
+        e (float, optional): Expansion ratio for CIB modules. Defaults to 0.5.
+    """
+
+    def __init__(self, c1, c2, n=1, shortcut=False, lk=False, g=1, e=0.5):
+        """Initializes the module with specified parameters for channel, shortcut, local key, groups, and expansion."""
+        super().__init__(c1, c2, n, shortcut, g, e)
+        self.m = nn.ModuleList(CIB(self.c, self.c, shortcut, e=1.0, lk=lk) for _ in range(n))
+
+
+class Attention(nn.Module):
+    """
+    Attention module that performs self-attention on the input tensor.
+
+    Args:
+        dim (int): The input tensor dimension.
+        num_heads (int): The number of attention heads.
+        attn_ratio (float): The ratio of the attention key dimension to the head dimension.
+
+    Attributes:
+        num_heads (int): The number of attention heads.
+        head_dim (int): The dimension of each attention head.
+        key_dim (int): The dimension of the attention key.
+        scale (float): The scaling factor for the attention scores.
+        qkv (Conv): Convolutional layer for computing the query, key, and value.
+        proj (Conv): Convolutional layer for projecting the attended values.
+        pe (Conv): Convolutional layer for positional encoding.
+    """
+
+    def __init__(self, dim, num_heads=8, attn_ratio=0.5):
+        """Initializes multi-head attention module with query, key, and value convolutions and positional encoding."""
+        super().__init__()
+        self.num_heads = num_heads
+        self.head_dim = dim // num_heads
+        self.key_dim = int(self.head_dim * attn_ratio)
+        self.scale = self.key_dim**-0.5
+        nh_kd = nh_kd = self.key_dim * num_heads
+        h = dim + nh_kd * 2
+        self.qkv = Conv(dim, h, 1, act=False)
+        self.proj = Conv(dim, dim, 1, act=False)
+        self.pe = Conv(dim, dim, 3, 1, g=dim, act=False)
+
+    def forward(self, x):
+        """
+        Forward pass of the Attention module.
+
+        Args:
+            x (torch.Tensor): The input tensor.
+
+        Returns:
+            (torch.Tensor): The output tensor after self-attention.
+        """
+        B, C, H, W = x.shape
+        N = H * W
+        qkv = self.qkv(x)
+        q, k, v = qkv.view(B, self.num_heads, self.key_dim * 2 + self.head_dim, N).split(
+            [self.key_dim, self.key_dim, self.head_dim], dim=2
+        )
+
+        attn = (q.transpose(-2, -1) @ k) * self.scale
+        attn = attn.softmax(dim=-1)
+        x = (v @ attn.transpose(-2, -1)).view(B, C, H, W) + self.pe(v.reshape(B, C, H, W))
+        x = self.proj(x)
+        return x
+
+
+class PSA(nn.Module):
+    """
+    Position-wise Spatial Attention module.
+
+    Args:
+        c1 (int): Number of input channels.
+        c2 (int): Number of output channels.
+        e (float): Expansion factor for the intermediate channels. Default is 0.5.
+
+    Attributes:
+        c (int): Number of intermediate channels.
+        cv1 (Conv): 1x1 convolution layer to reduce the number of input channels to 2*c.
+        cv2 (Conv): 1x1 convolution layer to reduce the number of output channels to c.
+        attn (Attention): Attention module for spatial attention.
+        ffn (nn.Sequential): Feed-forward network module.
+    """
+
+    def __init__(self, c1, c2, e=0.5):
+        """Initializes convolution layers, attention module, and feed-forward network with channel reduction."""
+        super().__init__()
+        assert c1 == c2
+        self.c = int(c1 * e)
+        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
+        self.cv2 = Conv(2 * self.c, c1, 1)
+
+        self.attn = Attention(self.c, attn_ratio=0.5, num_heads=self.c // 64)
+        self.ffn = nn.Sequential(Conv(self.c, self.c * 2, 1), Conv(self.c * 2, self.c, 1, act=False))
+
+    def forward(self, x):
+        """
+        Forward pass of the PSA module.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            (torch.Tensor): Output tensor.
+        """
+        a, b = self.cv1(x).split((self.c, self.c), dim=1)
+        b = b + self.attn(b)
+        b = b + self.ffn(b)
+        return self.cv2(torch.cat((a, b), 1))
+
+
+class SCDown(nn.Module):
+    def __init__(self, c1, c2, k, s):
+        """
+        Spatial Channel Downsample (SCDown) module.
+
+        Args:
+            c1 (int): Number of input channels.
+            c2 (int): Number of output channels.
+            k (int): Kernel size for the convolutional layer.
+            s (int): Stride for the convolutional layer.
+        """
+        super().__init__()
+        self.cv1 = Conv(c1, c2, 1, 1)
+        self.cv2 = Conv(c2, c2, k=k, s=s, g=c2, act=False)
+
+    def forward(self, x):
+        """
+        Forward pass of the SCDown module.
+
+        Args:
+            x (torch.Tensor): Input tensor.
+
+        Returns:
+            (torch.Tensor): Output tensor after applying the SCDown module.
+        """
+        return self.cv2(self.cv1(x))