Skip to content

Add YOLO11 P2 and P6 configs #73

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Y-T-G merged 19 commits into from
Apr 26, 2025
Merged

Add YOLO11 P2 and P6 configs #73

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
0ef0410
Merge pull request #57 from Y-T-G/scale-validation
Y-T-G Apr 26, 2025
4c9fcd9
Handle invalid `flops` and `params`
Y-T-G Apr 26, 2025
adbaaac
Support parsing list of FLOPs and parameters
Y-T-G Apr 26, 2025
b67b1d7
Add YOLO11-P2 Detect config (#56)
Y-T-G Apr 26, 2025
0039434
Add discussion link to detect/yolo11-p2.yaml
actions-user Apr 26, 2025
70cfb1a
Add YOLO11-P2 Segment config (#58)
Y-T-G Apr 26, 2025
a3e6ce3
Add YOLO11-OBB P2 config (#59)
Y-T-G Apr 26, 2025
899181c
Add discussion link to obb/yolo11-p2.yaml
actions-user Apr 26, 2025
bb188fc
Add discussion link to segment/yolo11-p2.yaml
Y-T-G Apr 26, 2025
9c3ddb4
Add YOLO11-Pose P2 config (#63)
Y-T-G Apr 26, 2025
8933204
Add discussion link to pose/yolo11-p2.yaml
actions-user Apr 26, 2025
496e325
Add YOLO11-Detect P6 config (#65)
Y-T-G Apr 26, 2025
350d2c3
Add discussion link to detect/yolo11-p6.yaml
actions-user Apr 26, 2025
3473218
Add YOLO11-Segment P6 config (#66)
Y-T-G Apr 26, 2025
fcdb6a0
Add discussion link to segment/yolo11-p6.yaml
actions-user Apr 26, 2025
50e8d26
Add YOLO11-Pose P6 config (#68)
Y-T-G Apr 26, 2025
4b96423
Add YOLO11-OBB P6 config (#67)
Y-T-G Apr 26, 2025
d395d01
Add discussion link to obb/yolo11-p6.yaml
actions-user Apr 26, 2025
23c2e33
Add discussion link to pose/yolo11-p6.yaml
Y-T-G Apr 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
87 changes: 87 additions & 0 deletions cfg/detect/yolo11-p2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,87 @@
# 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
discussion: https://github.com/Y-T-G/community/discussions/60

# 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
91 changes: 91 additions & 0 deletions cfg/detect/yolo11-p6.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
# Metadata
author: Y-T-G
task: detect
keywords: [cnn, yolo11, large-object]
description: YOLO11 detection model with an extra P6 scale for large object detecton.
flops:
n: 7.0
s: 23.2
m: 70.5
l: 90.3
x: 202.1
parameters:
n: 4391920
s: 16130064
m: 30063504
l: 37883024
x: 85074352
min_version: 8.3.0
discussion: https://github.com/Y-T-G/community/discussions/69

# Model
nc: 80
strides: [8, 16, 32, 64]
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, [768, True]] # (1, 512, 40, 40) - 6

# P5 Backbone
- [-1, 1, Conv, [768, 3, 2]] # (1, 512, 20, 20) - 7
- [-1, 2, C3k2, [768, True]] # (1, 512, 20, 20) - 8

# P6 Backbone
- [-1, 1, Conv, [1024, 3, 2]] # (1, 512, 10, 10) - 9
- [-1, 2, C3k2, [1024, True]] # (1, 512, 10, 10) - 10
- [-1, 1, SPPF, [1024, 5]] # (1, 512, 10, 10) - 11
- [-1, 2, C2PSA, [1024]] # (1, 512, 10, 10) - 12

head:
# Top-Down Path (Feature Pyramid)
# P5 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 20, 20) - 13
- [[-1, 8], 1, Concat, [1]] # (1, 1024, 20, 20) - 14
- [-1, 2, C3k2, [768, False]] # (1, 512, 20, 20) - 15

# P4 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 40, 40) - 16
- [[-1, 6], 1, Concat, [1]] # (1, 1024, 40, 40) - 17
- [-1, 2, C3k2, [512, False]] # (1, 512, 40, 40) - 18

# P3 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 80, 80) - 19
- [[-1, 4], 1, Concat, [1]] # (1, 1024, 80, 80) - 20
- [-1, 2, C3k2, [256, False]] # (1, 256, 80, 80) - 21

# Bottom-Up Path (PAN-FPN)
# P4
- [-1, 1, Conv, [256, 3, 2]] # (1, 256, 40, 40) - 22
- [[-1, 16], 1, Concat, [1]] # (1, 768, 40, 40) - 23
- [-1, 2, C3k2, [512, False]] # (1, 512, 40, 40) - 24

# P5
- [-1, 1, Conv, [512, 3, 2]] # (1, 512, 20, 20) - 25
- [[-1, 13], 1, Concat, [1]] # (1, 1024, 20, 20) - 26
- [-1, 2, C3k2, [768, True]] # (1, 512, 20, 20) - 27

# P6
- [-1, 1, Conv, [768, 3, 2]] # (1, 512, 10, 10) - 28
- [[-1, 10], 1, Concat, [1]] # (1, 1024, 10, 10) - 29
- [-1, 2, C3k2, [1024, True]] # (1, 512, 10, 10) - 30

# Detect Head (P3, P4, P5, P6)
- [[21, 24, 27, 30], 1, Detect, [nc]] # 31
87 changes: 87 additions & 0 deletions cfg/obb/yolo11-p2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,87 @@
# Metadata
author: Y-T-G
task: obb
keywords: [cnn, yolo11, small-object]
description: YOLO11 rotated bounding box model with an extra P2 scale for small object detecton.
flops:
n: 11.7
s: 30.7
m: 93.0
l: 117.6
x: 254.3
parameters:
n: 2777060
s: 9773748
m: 21034132
l: 26559380
x: 58845748
min_version: 8.3.0
discussion: https://github.com/Y-T-G/community/discussions/62

# 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

# OBB Head (P2, P3, P4, P5)
- [[19, 22, 25, 28], 1, OBB, [nc, 1]] # 29
91 changes: 91 additions & 0 deletions cfg/obb/yolo11-p6.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
# Metadata
author: Y-T-G
task: obb
keywords: [cnn, yolo11, large-object]
description: YOLO11 rotated bounding box model with an extra P6 scale for large object detecton.
flops:
n: 7.2
s: 24.2
m: 74.3
l: 94.1
x: 210.6
parameters:
n: 4493620
s: 16536212
m: 31244436
l: 39063956
x: 87730484
min_version: 8.3.0
discussion: https://github.com/Y-T-G/community/discussions/72

# Model
nc: 80
strides: [8, 16, 32, 64]
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, [768, True]] # (1, 512, 40, 40) - 6

# P5 Backbone
- [-1, 1, Conv, [768, 3, 2]] # (1, 512, 20, 20) - 7
- [-1, 2, C3k2, [768, True]] # (1, 512, 20, 20) - 8

# P6 Backbone
- [-1, 1, Conv, [1024, 3, 2]] # (1, 512, 10, 10) - 9
- [-1, 2, C3k2, [1024, True]] # (1, 512, 10, 10) - 10
- [-1, 1, SPPF, [1024, 5]] # (1, 512, 10, 10) - 11
- [-1, 2, C2PSA, [1024]] # (1, 512, 10, 10) - 12

head:
# Top-Down Path (Feature Pyramid)
# P5 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 20, 20) - 13
- [[-1, 8], 1, Concat, [1]] # (1, 1024, 20, 20) - 14
- [-1, 2, C3k2, [768, False]] # (1, 512, 20, 20) - 15

# P4 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 40, 40) - 16
- [[-1, 6], 1, Concat, [1]] # (1, 1024, 40, 40) - 17
- [-1, 2, C3k2, [512, False]] # (1, 512, 40, 40) - 18

# P3 Head
- [-1, 1, nn.Upsample, [None, 2, nearest]] # (1, 512, 80, 80) - 19
- [[-1, 4], 1, Concat, [1]] # (1, 1024, 80, 80) - 20
- [-1, 2, C3k2, [256, False]] # (1, 256, 80, 80) - 21

# Bottom-Up Path (PAN-FPN)
# P4
- [-1, 1, Conv, [256, 3, 2]] # (1, 256, 40, 40) - 22
- [[-1, 16], 1, Concat, [1]] # (1, 768, 40, 40) - 23
- [-1, 2, C3k2, [512, False]] # (1, 512, 40, 40) - 24

# P5
- [-1, 1, Conv, [512, 3, 2]] # (1, 512, 20, 20) - 25
- [[-1, 13], 1, Concat, [1]] # (1, 1024, 20, 20) - 26
- [-1, 2, C3k2, [768, True]] # (1, 512, 20, 20) - 27

# P6
- [-1, 1, Conv, [768, 3, 2]] # (1, 512, 10, 10) - 28
- [[-1, 10], 1, Concat, [1]] # (1, 1024, 10, 10) - 29
- [-1, 2, C3k2, [1024, True]] # (1, 512, 10, 10) - 30

# OBB Head (P3, P4, P5, P6)
- [[21, 24, 27, 30], 1, OBB, [nc, 1]] # 31
Loading