ultralytics-opencv-headless 8.3.242__py3-none-any.whl

ultralytics/cfg/models/v8/yolov8.yaml

@@ -0,0 +1,49 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLOv8 object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov8
+# 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 summary: 129 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPS
+  s: [0.33, 0.50, 1024] # YOLOv8s summary: 129 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPS
+  m: [0.67, 0.75, 768] # YOLOv8m summary: 169 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPS
+  l: [1.00, 1.00, 512] # YOLOv8l summary: 209 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPS
+  x: [1.00, 1.25, 512] # YOLOv8x summary: 209 layers, 68229648 parameters, 68229632 gradients, 258.5 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, C2f, [512]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 15 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 18 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2f, [1024]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9c-seg.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9c-seg instance segmentation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/segment
+# 380 layers, 27897120 parameters, 159.4 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]] # 2
+  - [-1, 1, ADown, [256]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]] # 4
+  - [-1, 1, ADown, [512]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 6
+  - [-1, 1, ADown, [512]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 8
+  - [-1, 1, SPPELAN, [512, 256]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]] # 15 (P3/8-small)
+
+  - [-1, 1, ADown, [256]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 18 (P4/16-medium)
+
+  - [-1, 1, ADown, [512]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9c.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9c object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 358 layers, 25590912 parameters, 104.0 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 1]] # 2
+  - [-1, 1, ADown, [256]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 1]] # 4
+  - [-1, 1, ADown, [512]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 6
+  - [-1, 1, ADown, [512]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 8
+  - [-1, 1, SPPELAN, [512, 256]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 1]] # 15 (P3/8-small)
+
+  - [-1, 1, ADown, [256]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 18 (P4/16-medium)
+
+  - [-1, 1, ADown, [512]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 1]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9e-seg.yaml

@@ -0,0 +1,64 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9e-seg instance segmentation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/segment
+# 743 layers, 60512800 parameters, 248.4 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, nn.Identity, []]
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 3
+  - [-1, 1, ADown, [256]] # 4-P3/8
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 5
+  - [-1, 1, ADown, [512]] # 6-P4/16
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 7
+  - [-1, 1, ADown, [1024]] # 8-P5/32
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 9
+
+  - [1, 1, CBLinear, [[64]]] # 10
+  - [3, 1, CBLinear, [[64, 128]]] # 11
+  - [5, 1, CBLinear, [[64, 128, 256]]] # 12
+  - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
+  - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
+
+  - [0, 1, Conv, [64, 3, 2]] # 15-P1/2
+  - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
+  - [-1, 1, Conv, [128, 3, 2]] # 17-P2/4
+  - [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 19
+  - [-1, 1, ADown, [256]] # 20-P3/8
+  - [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 22
+  - [-1, 1, ADown, [512]] # 23-P4/16
+  - [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 25
+  - [-1, 1, ADown, [1024]] # 26-P5/32
+  - [[14, -1], 1, CBFuse, [[4]]] # 27
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 28
+  - [-1, 1, SPPELAN, [512, 256]] # 29
+
+# GELAN head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 25], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 32
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 22], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]] # 35 (P3/8-small)
+
+  - [-1, 1, ADown, [256]]
+  - [[-1, 32], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 38 (P4/16-medium)
+
+  - [-1, 1, ADown, [512]]
+  - [[-1, 29], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]] # 41 (P5/32-large)
+
+  - [[35, 38, 41], 1, Segment, [nc, 32, 256]] # Segment (P3, P4, P5)

ultralytics/cfg/models/v9/yolov9e.yaml

@@ -0,0 +1,64 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9e object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 721 layers, 58206592 parameters, 193.0 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, nn.Identity, []]
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 2-P2/4
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 3
+  - [-1, 1, ADown, [256]] # 4-P3/8
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 5
+  - [-1, 1, ADown, [512]] # 6-P4/16
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 7
+  - [-1, 1, ADown, [1024]] # 8-P5/32
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 9
+
+  - [1, 1, CBLinear, [[64]]] # 10
+  - [3, 1, CBLinear, [[64, 128]]] # 11
+  - [5, 1, CBLinear, [[64, 128, 256]]] # 12
+  - [7, 1, CBLinear, [[64, 128, 256, 512]]] # 13
+  - [9, 1, CBLinear, [[64, 128, 256, 512, 1024]]] # 14
+
+  - [0, 1, Conv, [64, 3, 2]] # 15-P1/2
+  - [[10, 11, 12, 13, 14, -1], 1, CBFuse, [[0, 0, 0, 0, 0]]] # 16
+  - [-1, 1, Conv, [128, 3, 2]] # 17-P2/4
+  - [[11, 12, 13, 14, -1], 1, CBFuse, [[1, 1, 1, 1]]] # 18
+  - [-1, 1, RepNCSPELAN4, [256, 128, 64, 2]] # 19
+  - [-1, 1, ADown, [256]] # 20-P3/8
+  - [[12, 13, 14, -1], 1, CBFuse, [[2, 2, 2]]] # 21
+  - [-1, 1, RepNCSPELAN4, [512, 256, 128, 2]] # 22
+  - [-1, 1, ADown, [512]] # 23-P4/16
+  - [[13, 14, -1], 1, CBFuse, [[3, 3]]] # 24
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 25
+  - [-1, 1, ADown, [1024]] # 26-P5/32
+  - [[14, -1], 1, CBFuse, [[4]]] # 27
+  - [-1, 1, RepNCSPELAN4, [1024, 512, 256, 2]] # 28
+  - [-1, 1, SPPELAN, [512, 256]] # 29
+
+# GELAN head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 25], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 32
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 22], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 2]] # 35 (P3/8-small)
+
+  - [-1, 1, ADown, [256]]
+  - [[-1, 32], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [512, 512, 256, 2]] # 38 (P4/16-medium)
+
+  - [-1, 1, ADown, [512]]
+  - [[-1, 29], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [512, 1024, 512, 2]] # 41 (P5/32-large)
+
+  - [[35, 38, 41], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9m.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9m object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 348 layers, 20216160 parameters, 77.9 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [32, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P2/4
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 1]] # 2
+  - [-1, 1, AConv, [240]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [240, 240, 120, 1]] # 4
+  - [-1, 1, AConv, [360]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 6
+  - [-1, 1, AConv, [480]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [480, 480, 240, 1]] # 8
+  - [-1, 1, SPPELAN, [480, 240]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [240, 240, 120, 1]] # 15
+
+  - [-1, 1, AConv, [180]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [360, 360, 180, 1]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [240]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [480, 480, 240, 1]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v9/yolov9s.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9s object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 544 layers, 7318368 parameters, 27.6 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [32, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [64, 3, 2]] # 1-P2/4
+  - [-1, 1, ELAN1, [64, 64, 32]] # 2
+  - [-1, 1, AConv, [128]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 4
+  - [-1, 1, AConv, [192]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 6
+  - [-1, 1, AConv, [256]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 3]] # 8
+  - [-1, 1, SPPELAN, [256, 128]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 15
+
+  - [-1, 1, AConv, [96]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [192, 192, 96, 3]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [128]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [256, 256, 128, 3]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4 P5)

ultralytics/cfg/models/v9/yolov9t.yaml

@@ -0,0 +1,41 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# YOLOv9t object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolov9
+# Task docs: https://docs.ultralytics.com/tasks/detect
+# 544 layers, 2128720 parameters, 8.5 GFLOPs
+
+# Parameters
+nc: 80 # number of classes
+
+# GELAN backbone
+backbone:
+  - [-1, 1, Conv, [16, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [32, 3, 2]] # 1-P2/4
+  - [-1, 1, ELAN1, [32, 32, 16]] # 2
+  - [-1, 1, AConv, [64]] # 3-P3/8
+  - [-1, 1, RepNCSPELAN4, [64, 64, 32, 3]] # 4
+  - [-1, 1, AConv, [96]] # 5-P4/16
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 6
+  - [-1, 1, AConv, [128]] # 7-P5/32
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 8
+  - [-1, 1, SPPELAN, [128, 64]] # 9
+
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 1, RepNCSPELAN4, [64, 64, 32, 3]] # 15
+
+  - [-1, 1, AConv, [48]]
+  - [[-1, 12], 1, Concat, [1]] # cat head P4
+  - [-1, 1, RepNCSPELAN4, [96, 96, 48, 3]] # 18 (P4/16-medium)
+
+  - [-1, 1, AConv, [64]]
+  - [[-1, 9], 1, Concat, [1]] # cat head P5
+  - [-1, 1, RepNCSPELAN4, [128, 128, 64, 3]] # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/trackers/botsort.yaml

@@ -0,0 +1,21 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# BoT-SORT tracker defaults for mode="track"
+# Docs: https://docs.ultralytics.com/modes/track/
+
+tracker_type: botsort # (str) Tracker backend: botsort|bytetrack; choose botsort to enable BoT-SORT features
+track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
+track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
+new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
+track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
+match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
+fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections
+
+# BoT-SORT specifics
+gmc_method: sparseOptFlow # (str) Global motion compensation: sparseOptFlow|orb|none; helps moving camera scenes
+
+# ReID model related thresh
+proximity_thresh: 0.5 # (float) Min IoU to consider tracks proximate for ReID; higher is stricter
+appearance_thresh: 0.8 # (float) Min appearance similarity for ReID; raise to avoid identity swaps
+with_reid: False # (bool) Enable ReID model use; needs extra model and compute
+model: auto # (str) ReID model name/path; "auto" uses detector features if available

ultralytics/cfg/trackers/bytetrack.yaml

@@ -0,0 +1,12 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# ByteTrack tracker defaults for mode="track"
+# Docs: https://docs.ultralytics.com/modes/track/
+
+tracker_type: bytetrack # (str) Tracker backend: botsort|bytetrack; choose bytetrack for the classic baseline
+track_high_thresh: 0.25 # (float) First-stage match threshold; raise for cleaner tracks, lower to keep more
+track_low_thresh: 0.1 # (float) Second-stage threshold for low-score matches; balances recovery vs drift
+new_track_thresh: 0.25 # (float) Start a new track if no match ≥ this; higher reduces false tracks
+track_buffer: 30 # (int) Frames to keep lost tracks alive; higher handles occlusion, increases ID switches risk
+match_thresh: 0.8 # (float) Association similarity threshold (IoU/cost); tune with detector quality
+fuse_score: True # (bool) Fuse detection score with motion/IoU for matching; stabilizes weak detections

ultralytics/data/__init__.py

@@ -0,0 +1,26 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from .base import BaseDataset
+from .build import build_dataloader, build_grounding, build_yolo_dataset, load_inference_source
+from .dataset import (
+    ClassificationDataset,
+    GroundingDataset,
+    SemanticDataset,
+    YOLOConcatDataset,
+    YOLODataset,
+    YOLOMultiModalDataset,
+)
+
+__all__ = (
+    "BaseDataset",
+    "ClassificationDataset",
+    "GroundingDataset",
+    "SemanticDataset",
+    "YOLOConcatDataset",
+    "YOLODataset",
+    "YOLOMultiModalDataset",
+    "build_dataloader",
+    "build_grounding",
+    "build_yolo_dataset",
+    "load_inference_source",
+)

ultralytics/data/annotator.py

@@ -0,0 +1,66 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from ultralytics import SAM, YOLO
+
+
+def auto_annotate(
+    data: str | Path,
+    det_model: str = "yolo11x.pt",
+    sam_model: str = "sam_b.pt",
+    device: str = "",
+    conf: float = 0.25,
+    iou: float = 0.45,
+    imgsz: int = 640,
+    max_det: int = 300,
+    classes: list[int] | None = None,
+    output_dir: str | Path | None = None,
+) -> None:
+    """Automatically annotate images using a YOLO object detection model and a SAM segmentation model.
+
+    This function processes images in a specified directory, detects objects using a YOLO model, and then generates
+    segmentation masks using a SAM model. The resulting annotations are saved as text files in YOLO format.
+
+    Args:
+        data (str | Path): Path to a folder containing images to be annotated.
+        det_model (str): Path or name of the pre-trained YOLO detection model.
+        sam_model (str): Path or name of the pre-trained SAM segmentation model.
+        device (str): Device to run the models on (e.g., 'cpu', 'cuda', '0'). Empty string for auto-selection.
+        conf (float): Confidence threshold for detection model.
+        iou (float): IoU threshold for filtering overlapping boxes in detection results.
+        imgsz (int): Input image resize dimension.
+        max_det (int): Maximum number of detections per image.
+        classes (list[int], optional): Filter predictions to specified class IDs, returning only relevant detections.
+        output_dir (str | Path, optional): Directory to save the annotated results. If None, creates a default directory
+            based on the input data path.
+
+    Examples:
+        >>> from ultralytics.data.annotator import auto_annotate
+        >>> auto_annotate(data="ultralytics/assets", det_model="yolo11n.pt", sam_model="mobile_sam.pt")
+    """
+    det_model = YOLO(det_model)
+    sam_model = SAM(sam_model)
+
+    data = Path(data)
+    if not output_dir:
+        output_dir = data.parent / f"{data.stem}_auto_annotate_labels"
+    Path(output_dir).mkdir(exist_ok=True, parents=True)
+
+    det_results = det_model(
+        data, stream=True, device=device, conf=conf, iou=iou, imgsz=imgsz, max_det=max_det, classes=classes
+    )
+
+    for result in det_results:
+        if class_ids := result.boxes.cls.int().tolist():  # Extract class IDs from detection results
+            boxes = result.boxes.xyxy  # Boxes object for bbox outputs
+            sam_results = sam_model(result.orig_img, bboxes=boxes, verbose=False, save=False, device=device)
+            segments = sam_results[0].masks.xyn
+
+            with open(f"{Path(output_dir) / Path(result.path).stem}.txt", "w", encoding="utf-8") as f:
+                for i, s in enumerate(segments):
+                    if s.any():
+                        segment = map(str, s.reshape(-1).tolist())
+                        f.write(f"{class_ids[i]} " + " ".join(segment) + "\n")