Add YOLO8x6 and YAML syntax improvements (#120)

This commit is contained in:
Glenn Jocher
2022-12-30 13:32:08 +01:00
committed by GitHub
parent 076d73cfaa
commit fec13ec773
13 changed files with 319 additions and 292 deletions

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.00 # layer channel multiple
depth_multiple: 1.00 # scales module repeats
width_multiple: 1.00 # scales convolution channels
# YOLOv8.0l backbone
backbone:
# [from, number, 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, [512, 3, 2]], # 7-P5/32
[-1, 3, C2f, [512, True]],
[-1, 1, SPPF, [512, 5]], # 9
]
# [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, [512, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [512, True]]
- [-1, 1, SPPF, [512, 5]] # 9
# YOLOv8.0l 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [512]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
[[15, 18, 21], 1, Segment, [nc, 32, 256]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.67 # model depth multiple
width_multiple: 0.75 # layer channel multiple
depth_multiple: 0.67 # scales module repeats
width_multiple: 0.75 # scales convolution channels
# YOLOv8.0m backbone
backbone:
# [from, number, 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, [768, 3, 2]], # 7-P5/32
[-1, 3, C2f, [768, True]],
[-1, 1, SPPF, [768, 5]], # 9
]
# [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, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, SPPF, [768, 5]] # 9
# YOLOv8.0m 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [768]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [768]] # 23 (P5/32-large)
[[15, 18, 21], 1, Segment, [nc, 32, 256]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.25 # layer channel multiple
depth_multiple: 0.33 # scales module repeats
width_multiple: 0.25 # scales convolution channels
# YOLOv8.0n backbone
backbone:
# [from, number, 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
]
# [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, C2f, [512]], # 13
- [-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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [1024]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
[[15, 18, 21], 1, Segment, [nc, 32, 256]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
depth_multiple: 0.33 # scales module repeats
width_multiple: 0.50 # scales convolution channels
# YOLOv8.0s backbone
backbone:
# [from, number, 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
]
# [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
# YOLOv8.0s 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [1024]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
[[15, 18, 21], 1, Segment, [nc, 32, 256]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.25 # layer channel multiple
depth_multiple: 1.00 # scales module repeats
width_multiple: 1.25 # scales convolution channels
# YOLOv8.0x backbone
backbone:
# [from, number, 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, [512, 3, 2]], # 7-P5/32
[-1, 3, C2f, [512, True]],
[-1, 1, SPPF, [512, 5]], # 9
]
# [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, [512, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [512, True]]
- [-1, 1, SPPF, [512, 5]] # 9
# YOLOv8.0x 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [512]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
[[15, 18, 21], 1, Segment, [nc, 32, 256]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.00 # layer channel multiple
depth_multiple: 1.00 # scales module repeats
width_multiple: 1.00 # scales convolution channels
# YOLOv8.0l backbone
backbone:
# [from, number, 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, [512, 3, 2]], # 7-P5/32
[-1, 3, C2f, [512, True]],
[-1, 1, SPPF, [512, 5]], # 9
]
# [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, [512, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [512, True]]
- [-1, 1, SPPF, [512, 5]] # 9
# YOLOv8.0l 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [512]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
[[15, 18, 21], 1, Detect, [nc]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.67 # model depth multiple
width_multiple: 0.75 # layer channel multiple
depth_multiple: 0.67 # scales module repeats
width_multiple: 0.75 # scales convolution channels
# YOLOv8.0m backbone
backbone:
# [from, number, 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, [768, 3, 2]], # 7-P5/32
[-1, 3, C2f, [768, True]],
[-1, 1, SPPF, [768, 5]], # 9
]
# [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, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, SPPF, [768, 5]] # 9
# YOLOv8.0m 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [768]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [768]] # 23 (P5/32-large)
[[15, 18, 21], 1, Detect, [nc]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.25 # layer channel multiple
depth_multiple: 0.33 # scales module repeats
width_multiple: 0.25 # scales convolution channels
# YOLOv8.0n backbone
backbone:
# [from, number, 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
]
# [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, C2f, [512]], # 13
- [-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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [1024]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
[[15, 18, 21], 1, Detect, [nc]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
depth_multiple: 0.33 # scales module repeats
width_multiple: 0.50 # scales convolution channels
# YOLOv8.0s backbone
backbone:
# [from, number, 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
]
# [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
# YOLOv8.0s 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [1024]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 23 (P5/32-large)
[[15, 18, 21], 1, Detect, [nc]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

View File

@ -2,41 +2,39 @@
# Parameters
nc: 80 # number of classes
depth_multiple: 1.00 # model depth multiple
width_multiple: 1.25 # layer channel multiple
depth_multiple: 1.00 # scales module repeats
width_multiple: 1.25 # scales convolution channels
# YOLOv8.0x backbone
backbone:
# [from, number, 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, [512, 3, 2]], # 7-P5/32
[-1, 3, C2f, [512, True]],
[-1, 1, SPPF, [512, 5]], # 9
]
# [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, [512, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [512, True]]
- [-1, 1, SPPF, [512, 5]] # 9
# YOLOv8.0x 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, 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]], # 17 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 12], 1, Concat, [1]], # cat head P4
[-1, 3, C2f, [512]], # 20 (P4/16-medium)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 9], 1, Concat, [1]], # cat head P5
[-1, 3, C2f, [512]], # 23 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [512]] # 23 (P5/32-large)
[[15, 18, 21], 1, Detect, [nc]], # Detect(P3, P4, P5)
]
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

View File

@ -0,0 +1,50 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 80 # number of classes
depth_multiple: 1.00 # scales module repeats
width_multiple: 1.25 # scales convolution channels
# YOLOv8.0x6 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, [512, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [512, True]]
- [-1, 1, Conv, [512, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [512, True]]
- [-1, 1, SPPF, [512, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [512, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [512, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [512, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)