Add YOLO11-P2 Detect config (#56)

* Add YOLO11-P2 Detect config

* Update output shapes

* Update FLOPs and parameters

Author: Y-T-G

cfg/detect/yolo11-p2.yaml

@@ -0,0 +1,86 @@
+# Metadata
+author: Y-T-G
+task: detect
+keywords: [cnn, yolo11, small-object]
+description: YOLO11 object detection model with an extra P2 scale for small object detecton.
+flops:
+  n: 11.4
+  s: 29.7
+  m: 88.9
+  l: 113.6
+  x: 245.1
+parameters:
+  n: 2740032
+  s: 9625968
+  m: 20591120
+  l: 26116368
+  x: 57849456
+min_version: 8.3.0
+
+# Model
+nc: 80
+strides: [4, 8, 16, 32]
+scales:
+  n: [0.50, 0.25, 1024]
+  s: [0.50, 0.50, 1024]
+  m: [0.50, 1.00, 512]
+  l: [1.00, 1.00, 512] 
+  x: [1.00, 1.50, 512] 
+
+backbone:
+  # Stem
+  - [-1, 1, Conv, [64, 3, 2]]                   # (1, 64, 320, 320) - 0
+
+  # P2 Backbone
+  - [-1, 1, Conv, [128, 3, 2]]                  # (1, 128, 160, 160) - 1
+  - [-1, 2, C3k2, [256, False, 0.25]]           # (1, 256, 160, 160) - 2
+
+  # P3 Backbone
+  - [-1, 1, Conv, [256, 3, 2]]                  # (1, 256, 80, 80) - 3
+  - [-1, 2, C3k2, [512, False, 0.25]]           # (1, 512, 80, 80) - 4
+
+  # P4 Backbone
+  - [-1, 1, Conv, [512, 3, 2]]                  # (1, 512, 40, 40) - 5
+  - [-1, 2, C3k2, [512, True]]                  # (1, 512, 40, 40) - 6
+
+  # P5 Backbone
+  - [-1, 1, Conv, [1024, 3, 2]]                 # (1, 512, 20, 20) - 7
+  - [-1, 2, C3k2, [1024, True]]                 # (1, 512, 20, 20) - 8
+  - [-1, 1, SPPF, [1024, 5]]                    # (1, 512, 20, 20) - 9
+  - [-1, 2, C2PSA, [1024]]                      # (1, 512, 20, 20) - 10
+
+head:
+  # Top-Down Path (Feature Pyramid)
+  # P4 Head
+  - [-1, 1, nn.Upsample, [None, 2, nearest]]    # (1, 512, 40, 40) - 11
+  - [[-1, 6], 1, Concat, [1]]                   # (1, 1024, 40, 40) - 12
+  - [-1, 2, C3k2, [512, False]]                 # (1, 512, 40, 40) - 13
+
+  # P3 Head
+  - [-1, 1, nn.Upsample, [None, 2, nearest]]    # (1, 512, 80, 80) - 14
+  - [[-1, 4], 1, Concat, [1]]                   # (1, 1024, 80, 80) - 15
+  - [-1, 2, C3k2, [256, False]]                 # (1, 256, 80, 80) - 16
+
+  # P2 Head
+  - [-1, 1, nn.Upsample, [None, 2, nearest]]    # (1, 256, 160, 160) - 17
+  - [[-1, 2], 1, Concat, [1]]                   # (1, 512, 160, 160) - 18
+  - [-1, 2, C3k2, [128, False]]                 # (1, 128, 160, 160) - 19
+
+  # Bottom-Up Path (PAN-FPN)
+  # P3
+  - [-1, 1, Conv, [128, 3, 2]]                  # (1, 128, 80, 80) - 20
+  - [[-1, 16], 1, Concat, [1]]                  # (1, 384, 80, 80) - 21
+  - [-1, 2, C3k2, [256, False]]                 # (1, 256, 80, 80) - 22
+
+  # P4
+  - [-1, 1, Conv, [256, 3, 2]]                  # (1, 256, 40, 40) - 23
+  - [[-1, 13], 1, Concat, [1]]                  # (1, 768, 40, 40) - 24
+  - [-1, 2, C3k2, [512, False]]                 # (1, 512, 40, 40) - 25
+
+  # P5
+  - [-1, 1, Conv, [512, 3, 2]]                  # (1, 512, 20, 20) - 26
+  - [[-1, 10], 1, Concat, [1]]                  # (1, 1024, 20, 20) - 27
+  - [-1, 2, C3k2, [1024, True]]                 # (1, 512, 20, 20) - 28
+
+  # Detection Head (P2, P3, P4, P5)
+  - [[19, 22, 25, 28], 1, Detect, [nc]]         # 29