init commit

ultralytics/cfg/models/v8/yolov8-world.yaml

@@ -0,0 +1,51 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLOv8-World hybrid object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo-world
+# Task docs: 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-world summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOv8s-world summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOv8m-world summary: 201 layers, 29065310 parameters, 29065294 gradients, 131.4 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOv8l-world summary: 241 layers, 47553970 parameters, 47553954 gradients, 225.6 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOv8x-world summary: 241 layers, 73690217 parameters, 73690201 gradients, 330.8 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, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2f, [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, 3, C2fAttn, [512, 256, 8]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small)
+
+  - [[15, 12, 9], 1, ImagePoolingAttn, [256]] # 16 (P3/8-small)
+
+  - [15, 1, Conv, [256, 3, 2]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fAttn, [512, 256, 8]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fAttn, [1024, 512, 16]] # 22 (P5/32-large)
+
+  - [[15, 19, 22], 1, WorldDetect, [nc, 512, False]] # Detect(P3, P4, P5)