From d5b7d37d2475484bfa1326339dc5bfe43346bf11 Mon Sep 17 00:00:00 2001
From: Laughing-q <1185102784@qq.com>
Date: Thu, 25 Apr 2024 15:50:59 +0800
Subject: [PATCH] update C3K2

---
 .../cfg/models/exp/yolov8-c3K2-2222-True.yaml | 46 +++++++++++++++++++
 ultralytics/nn/modules/block.py               |  3 +-
 2 files changed, 48 insertions(+), 1 deletion(-)
 create mode 100644 ultralytics/cfg/models/exp/yolov8-c3K2-2222-True.yaml

diff --git a/ultralytics/cfg/models/exp/yolov8-c3K2-2222-True.yaml b/ultralytics/cfg/models/exp/yolov8-c3K2-2222-True.yaml
new file mode 100644
index 000000000..ecc695089
--- /dev/null
+++ b/ultralytics/cfg/models/exp/yolov8-c3K2-2222-True.yaml
@@ -0,0 +1,46 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv8 object detection model with P3-P5 outputs. 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] # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
+
+# YOLOv8.0n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 2, C3K2, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3K2, [256, True]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 2, C3K2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3K2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3K2, [512, True]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3K2, [256, True]] # 15 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3K2, [512, True]] # 18 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3K2, [1024, True]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
diff --git a/ultralytics/nn/modules/block.py b/ultralytics/nn/modules/block.py
index a65f708e6..3b3bc8b24 100644
--- a/ultralytics/nn/modules/block.py
+++ b/ultralytics/nn/modules/block.py
@@ -362,7 +362,8 @@ class C3K(C3):
     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 channels
-        self.cv2 = Conv(c1, c_, 3, 1)
+        # self.cv2 = Conv(c1, c_, 3, 1)
+        self.cv3 = Conv(2 * c_, c2, 3)  # optional act=FReLU(c2)
         self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(3, 3), e=1.0) for _ in range(n)))