2025-03-26 11:26:55 +08:00

50 lines
2.1 KiB
YAML

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-Worldv2 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-worldv2 summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPS
s: [0.33, 0.50, 1024] # YOLOv8s-worldv2 summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPS
m: [0.67, 0.75, 768] # YOLOv8m-worldv2 summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPS
l: [1.00, 1.00, 512] # YOLOv8l-worldv2 summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPS
x: [1.00, 1.25, 512] # YOLOv8x-worldv2 summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 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, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fAttn, [1024, 512, 16]] # 21 (P5/32-large)
- [[15, 18, 21], 1, WorldDetect, [nc, 512, True]] # Detect(P3, P4, P5)