dgenerate-ultralytics-headless 8.3.134__py3-none-any.whl

ultralytics/cfg/models/12/yolo12-cls.yaml

@@ -0,0 +1,32 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-cls image classification model
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/classify
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-cls.yaml' will call yolo12-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 152 layers, 1,820,976 parameters, 1,820,976 gradients, 3.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 152 layers, 6,206,992 parameters, 6,206,992 gradients, 13.6 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 172 layers, 12,083,088 parameters, 12,083,088 gradients, 44.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 312 layers, 15,558,640 parameters, 15,558,640 gradients, 56.9 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 312 layers, 34,172,592 parameters, 34,172,592 gradients, 126.5 GFLOPs
+
+# YOLO12n 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, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, Classify, [nc]] # Classify

ultralytics/cfg/models/12/yolo12-obb.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/obb
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-obb.yaml' will call yolo12-obb.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 287 layers, 2,673,955 parameters, 2,673,939 gradients, 6.9 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 287 layers, 9,570,275 parameters, 9,570,259 gradients, 22.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 307 layers, 21,048,003 parameters, 21,047,987 gradients, 71.8 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 503 layers, 27,299,619 parameters, 27,299,603 gradients, 93.4 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 503 layers, 61,119,939 parameters, 61,119,923 gradients, 208.6 GFLOPs
+
+# YOLO12n 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, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12-pose.yaml

@@ -0,0 +1,49 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/pose
+
+# Parameters
+nc: 80 # number of classes
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+scales: # model compound scaling constants, i.e. 'model=yolo12n-pose.yaml' will call yolo12-pose.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 287 layers, 2,886,715 parameters, 2,886,699 gradients, 7.8 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 287 layers, 9,774,155 parameters, 9,774,139 gradients, 23.5 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 307 layers, 21,057,753 parameters, 21,057,737 gradients, 71.8 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 503 layers, 27,309,369 parameters, 27,309,353 gradients, 93.5 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 503 layers, 61,134,489 parameters, 61,134,473 gradients, 208.7 GFLOPs
+
+# YOLO12n 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, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Pose, [nc, kpt_shape]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12-seg.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12-seg instance segmentation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/segment
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n-seg.yaml' will call yolo12-seg.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 294 layers, 2,855,056 parameters, 2,855,040 gradients, 10.6 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 294 layers, 9,938,592 parameters, 9,938,576 gradients, 35.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 314 layers, 22,505,376 parameters, 22,505,360 gradients, 123.5 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 510 layers, 28,756,992 parameters, 28,756,976 gradients, 145.1 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 510 layers, 64,387,264 parameters, 64,387,248 gradients, 324.6 GFLOPs
+
+# YOLO12n 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, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

ultralytics/cfg/models/12/yolo12.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLO12 object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo12
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo12n.yaml' will call yolo12.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 272 layers, 2,602,288 parameters, 2,602,272 gradients, 6.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 272 layers, 9,284,096 parameters, 9,284,080 gradients, 21.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 292 layers, 20,199,168 parameters, 20,199,152 gradients, 68.1 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 488 layers, 26,450,784 parameters, 26,450,768 gradients, 89.7 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 488 layers, 59,210,784 parameters, 59,210,768 gradients, 200.3 GFLOPs
+
+# YOLO12n 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, 2, C3k2, [256, False, 0.25]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 2, C3k2, [512, False, 0.25]]
+  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
+  - [-1, 4, A2C2f, [512, True, 4]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 4, A2C2f, [1024, True, 1]] # 8
+
+# YOLO12n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 11
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, A2C2f, [256, False, -1]] # 14
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 11], 1, Concat, [1]] # cat head P4
+  - [-1, 2, A2C2f, [512, False, -1]] # 17
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 8], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
+
+  - [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/rt-detr/rtdetr-l.yaml

@@ -0,0 +1,53 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics RT-DETR-l hybrid object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/rtdetr
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, HGStem, [32, 48]] # 0-P2/4
+  - [-1, 6, HGBlock, [48, 128, 3]] # stage 1
+
+  - [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
+  - [-1, 6, HGBlock, [96, 512, 3]] # stage 2
+
+  - [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P3/16
+  - [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
+  - [-1, 6, HGBlock, [192, 1024, 5, True, True]]
+  - [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
+
+  - [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P4/32
+  - [-1, 6, HGBlock, [384, 2048, 5, True, False]] # stage 4
+
+head:
+  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
+  - [-1, 1, AIFI, [1024, 8]]
+  - [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
+  - [[-2, -1], 1, Concat, [1]]
+  - [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
+  - [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
+  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
+
+  - [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
+  - [[-1, 17], 1, Concat, [1]] # cat Y4
+  - [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
+
+  - [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
+  - [[-1, 12], 1, Concat, [1]] # cat Y5
+  - [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
+
+  - [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics RT-DETR-ResNet101 hybrid object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/rtdetr
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
+  - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
+  - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
+  - [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3
+  - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
+
+head:
+  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
+  - [-1, 1, AIFI, [1024, 8]]
+  - [-1, 1, Conv, [256, 1, 1]] # 7
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
+  - [[-2, -1], 1, Concat, [1]]
+  - [-1, 3, RepC3, [256]] # 11
+  - [-1, 1, Conv, [256, 1, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
+  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
+
+  - [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
+  - [[-1, 12], 1, Concat, [1]] # cat Y4
+  - [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
+
+  - [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
+  - [[-1, 7], 1, Concat, [1]] # cat Y5
+  - [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
+
+  - [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics RT-DETR-ResNet50 hybrid object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/rtdetr
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
+  - [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
+  - [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
+  - [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3
+  - [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
+
+head:
+  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
+  - [-1, 1, AIFI, [1024, 8]]
+  - [-1, 1, Conv, [256, 1, 1]] # 7
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
+  - [[-2, -1], 1, Concat, [1]]
+  - [-1, 3, RepC3, [256]] # 11
+  - [-1, 1, Conv, [256, 1, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
+  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
+
+  - [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
+  - [[-1, 12], 1, Concat, [1]] # cat Y4
+  - [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
+
+  - [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
+  - [[-1, 7], 1, Concat, [1]] # cat Y5
+  - [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
+
+  - [[16, 19, 22], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/rt-detr/rtdetr-x.yaml

@@ -0,0 +1,57 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics RT-DETR-x hybrid object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/rtdetr
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  x: [1.00, 1.00, 2048]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, HGStem, [32, 64]] # 0-P2/4
+  - [-1, 6, HGBlock, [64, 128, 3]] # stage 1
+
+  - [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
+  - [-1, 6, HGBlock, [128, 512, 3]]
+  - [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2
+
+  - [-1, 1, DWConv, [512, 3, 2, 1, False]] # 5-P3/16
+  - [-1, 6, HGBlock, [256, 1024, 5, True, False]] # cm, c2, k, light, shortcut
+  - [-1, 6, HGBlock, [256, 1024, 5, True, True]]
+  - [-1, 6, HGBlock, [256, 1024, 5, True, True]]
+  - [-1, 6, HGBlock, [256, 1024, 5, True, True]]
+  - [-1, 6, HGBlock, [256, 1024, 5, True, True]] # 10-stage 3
+
+  - [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 11-P4/32
+  - [-1, 6, HGBlock, [512, 2048, 5, True, False]]
+  - [-1, 6, HGBlock, [512, 2048, 5, True, True]] # 13-stage 4
+
+head:
+  - [-1, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 14 input_proj.2
+  - [-1, 1, AIFI, [2048, 8]]
+  - [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [10, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 18 input_proj.1
+  - [[-2, -1], 1, Concat, [1]]
+  - [-1, 3, RepC3, [384]] # 20, fpn_blocks.0
+  - [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [4, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 23 input_proj.0
+  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1
+
+  - [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0
+  - [[-1, 21], 1, Concat, [1]] # cat Y4
+  - [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0
+
+  - [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1
+  - [[-1, 16], 1, Concat, [1]] # cat Y5
+  - [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1
+
+  - [[25, 28, 31], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10b.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv10b object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov10
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+  # [depth, width, max_channels]
+  b: [0.67, 1.00, 512]
+
+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, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv10.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10l.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv10l object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov10
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 512]
+
+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, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv10.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10m.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv10m object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov10
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+  # [depth, width, max_channels]
+  m: [0.67, 0.75, 768]
+
+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, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv10.0n 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, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10n.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv10n object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov10
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+
+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, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv10.0n 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, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10s.yaml

@@ -0,0 +1,45 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv10s object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov10
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+  # [depth, width, max_channels]
+  s: [0.33, 0.50, 1024]
+
+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, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv10.0n 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, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)