ultralytics 8.1.29__py3-none-any.whl → 8.3.62__py3-none-any.whl

ultralytics/cfg/datasets/medical-pills.yaml

@@ -0,0 +1,22 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Medical-pills dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/medical-pills/
+# Example usage: yolo train data=medical-pills.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── medical-pills  ← downloads here (8.19 MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/medical-pills # dataset root dir
+train: train/images # train images (relative to 'path') 92 images
+val: valid/images # val images (relative to 'path') 23 images
+test: # test images (relative to 'path')
+
+# Classes
+names:
+  0: pill
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/medical-pills.zip

ultralytics/cfg/datasets/open-images-v7.yaml

@@ -1,4 +1,5 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
 # Open Images v7 dataset https://storage.googleapis.com/openimages/web/index.html by Google
 # Documentation: https://docs.ultralytics.com/datasets/detect/open-images-v7/
 # Example usage: yolo train data=open-images-v7.yaml

ultralytics/cfg/datasets/package-seg.yaml

@@ -1,4 +1,5 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
 # Package-seg dataset by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/segment/package-seg/
 # Example usage: yolo train data=package-seg.yaml
@@ -9,8 +10,8 @@
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
 path: ../datasets/package-seg # dataset root dir
-train: images/train # train images (relative to 'path') 1920 images
-val: images/val # val images (relative to 'path') 89 images
+train: train/images # train images (relative to 'path') 1920 images
+val: valid/images # val images (relative to 'path') 89 images
 test: test/images # test images (relative to 'path') 188 images
 
 # Classes
@@ -18,4 +19,4 @@ names:
   0: package
 
 # Download script/URL (optional)
-download: https://ultralytics.com/assets/package-seg.zip
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/package-seg.zip

ultralytics/cfg/datasets/signature.yaml

@@ -0,0 +1,21 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Signature dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/signature/
+# Example usage: yolo train data=signature.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── signature  ← downloads here (11.2 MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/signature # dataset root dir
+train: train/images # train images (relative to 'path') 143 images
+val: valid/images # val images (relative to 'path') 35 images
+
+# Classes
+names:
+  0: signature
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/signature.zip

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -1,4 +1,5 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
 # Tiger Pose dataset by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/pose/tiger-pose/
 # Example usage: yolo train data=tiger-pose.yaml
@@ -21,4 +22,4 @@ names:
   0: tiger
 
 # Download script/URL (optional)
-download: https://ultralytics.com/assets/tiger-pose.zip
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/tiger-pose.zip

ultralytics/cfg/datasets/xView.yaml

@@ -1,4 +1,5 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
 # DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
 # --------  DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running train command!  --------
 # Documentation: https://docs.ultralytics.com/datasets/detect/xview/

ultralytics/cfg/default.yaml

@@ -1,17 +1,19 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Default training settings and hyperparameters for medium-augmentation COCO training
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
+# Global configuration YAML with settings and hyperparameters for YOLO training, validation, prediction and export
+# For documentation see https://docs.ultralytics.com/usage/cfg/
+
+task: detect # (str) YOLO task, i.e. detect, segment, classify, pose, obb
 mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark
 
 # Train settings -------------------------------------------------------------------------------------------------------
 model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml
-data: # (str, optional) path to data file, i.e. coco128.yaml
+data: # (str, optional) path to data file, i.e. coco8.yaml
 epochs: 100 # (int) number of epochs to train for
 time: # (float, optional) number of hours to train for, overrides epochs if supplied
 patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
 batch: 16 # (int) number of images per batch (-1 for AutoBatch)
-imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
+imgsz: 640 # (int | list) input images size as int for train and val modes, or list[h,w] for predict and export modes
 save: True # (bool) save train checkpoints and predict results
 save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
 cache: False # (bool) True/ram, disk or False. Use cache for data loading
@@ -36,7 +38,7 @@ profile: False # (bool) profile ONNX and TensorRT speeds during training for log
 freeze: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training
 multi_scale: False # (bool) Whether to use multiscale during training
 # Segmentation
-overlap_mask: True # (bool) masks should overlap during training (segment train only)
+overlap_mask: True # (bool) merge object masks into a single image mask during training (segment train only)
 mask_ratio: 4 # (int) mask downsample ratio (segment train only)
 # Classification
 dropout: 0.0 # (float) use dropout regularization (classify train only)
@@ -81,9 +83,9 @@ keras: False # (bool) use Kera=s
 optimize: False # (bool) TorchScript: optimize for mobile
 int8: False # (bool) CoreML/TF INT8 quantization
 dynamic: False # (bool) ONNX/TF/TensorRT: dynamic axes
-simplify: False # (bool) ONNX: simplify model
+simplify: True # (bool) ONNX: simplify model using `onnxslim`
 opset: # (int, optional) ONNX: opset version
-workspace: 4 # (int) TensorRT: workspace size (GB)
+workspace: None # (float, optional) TensorRT: workspace size (GiB), `None` will let TensorRT auto-allocate memory
 nms: False # (bool) CoreML: add NMS
 
 # Hyperparameters ------------------------------------------------------------------------------------------------------
@@ -99,7 +101,6 @@ cls: 0.5 # (float) cls loss gain (scale with pixels)
 dfl: 1.5 # (float) dfl loss gain
 pose: 12.0 # (float) pose loss gain
 kobj: 1.0 # (float) keypoint obj loss gain
-label_smoothing: 0.0 # (float) label smoothing (fraction)
 nbs: 64 # (int) nominal batch size
 hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
 hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
@@ -111,12 +112,14 @@ shear: 0.0 # (float) image shear (+/- deg)
 perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
 flipud: 0.0 # (float) image flip up-down (probability)
 fliplr: 0.5 # (float) image flip left-right (probability)
+bgr: 0.0 # (float) image channel BGR (probability)
 mosaic: 1.0 # (float) image mosaic (probability)
 mixup: 0.0 # (float) image mixup (probability)
 copy_paste: 0.0 # (float) segment copy-paste (probability)
+copy_paste_mode: "flip" # (str) the method to do copy_paste augmentation (flip, mixup)
 auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix)
-erasing: 0.4 # (float) probability of random erasing during classification training (0-1)
-crop_fraction: 1.0 # (float) image crop fraction for classification evaluation/inference (0-1)
+erasing: 0.4 # (float) probability of random erasing during classification training (0-0.9), 0 means no erasing, must be less than 1.0.
+crop_fraction: 1.0 # (float) image crop fraction for classification (0.1-1), 1.0 means no crop, must be greater than 0.
 
 # Custom config.yaml ---------------------------------------------------------------------------------------------------
 cfg: # (str, optional) for overriding defaults.yaml

ultralytics/cfg/models/11/yolo11-cls-resnet18.yaml

@@ -0,0 +1,24 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-cls image classification model with ResNet18 backbone
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/classify
+
+# Parameters
+nc: 10 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-cls.yaml' will call yolo11-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+  s: [0.33, 0.50, 1024]
+  m: [0.67, 0.75, 1024]
+  l: [1.00, 1.00, 1024]
+  x: [1.00, 1.25, 1024]
+
+# ResNet18 backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, TorchVision, [512, "resnet18", "DEFAULT", True, 2]] # truncate two layers from the end
+
+# YOLO11n head
+head:
+  - [-1, 1, Classify, [nc]] # Classify

ultralytics/cfg/models/11/yolo11-cls.yaml

@@ -0,0 +1,33 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-cls image classification model
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/classify
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-cls.yaml' will call yolo11-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 151 layers, 1633584 parameters, 1633584 gradients, 3.3 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 151 layers, 5545488 parameters, 5545488 gradients, 12.2 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 187 layers, 10455696 parameters, 10455696 gradients, 39.7 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 309 layers, 12937104 parameters, 12937104 gradients, 49.9 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 309 layers, 28458544 parameters, 28458544 gradients, 111.1 GFLOPs
+
+# YOLO11n 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, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 2, C2PSA, [1024]] # 9
+
+# YOLO11n head
+head:
+  - [-1, 1, Classify, [nc]] # Classify

ultralytics/cfg/models/11/yolo11-obb.yaml

@@ -0,0 +1,50 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/obb
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-obb.yaml' will call yolo11-obb.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 344 layers, 2695747 parameters, 2695731 gradients, 6.9 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 344 layers, 9744931 parameters, 9744915 gradients, 22.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 434 layers, 20963523 parameters, 20963507 gradients, 72.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 656 layers, 26220995 parameters, 26220979 gradients, 91.3 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 656 layers, 58875331 parameters, 58875315 gradients, 204.3 GFLOPs
+
+# YOLO11n 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, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 2, C2PSA, [1024]] # 10
+
+# YOLO11n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3k2, [512, False]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, OBB, [nc, 1]] # Detect(P3, P4, P5)

ultralytics/cfg/models/11/yolo11-pose.yaml

@@ -0,0 +1,51 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# 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=yolo11n-pose.yaml' will call yolo11.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 344 layers, 2908507 parameters, 2908491 gradients, 7.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 344 layers, 9948811 parameters, 9948795 gradients, 23.5 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 434 layers, 20973273 parameters, 20973257 gradients, 72.3 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 656 layers, 26230745 parameters, 26230729 gradients, 91.4 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 656 layers, 58889881 parameters, 58889865 gradients, 204.3 GFLOPs
+
+# YOLO11n 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, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 2, C2PSA, [1024]] # 10
+
+# YOLO11n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3k2, [512, False]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, Pose, [nc, kpt_shape]] # Detect(P3, P4, P5)

ultralytics/cfg/models/11/yolo11-seg.yaml

@@ -0,0 +1,50 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11-seg instance segmentation model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/segment
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n-seg.yaml' will call yolo11-seg.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 355 layers, 2876848 parameters, 2876832 gradients, 10.5 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 355 layers, 10113248 parameters, 10113232 gradients, 35.8 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 445 layers, 22420896 parameters, 22420880 gradients, 123.9 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 667 layers, 27678368 parameters, 27678352 gradients, 143.0 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 667 layers, 62142656 parameters, 62142640 gradients, 320.2 GFLOPs
+
+# YOLO11n 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, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 2, C2PSA, [1024]] # 10
+
+# YOLO11n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3k2, [512, False]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, Segment, [nc, 32, 256]] # Detect(P3, P4, P5)

ultralytics/cfg/models/11/yolo11.yaml

@@ -0,0 +1,50 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLO11 object detection model with P3/8 - P5/32 outputs
+# Model docs: https://docs.ultralytics.com/models/yolo11
+# Task docs: https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
+
+# YOLO11n 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, 2, C3k2, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
+  - [-1, 2, C3k2, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 2, C2PSA, [1024]] # 10
+
+# YOLO11n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 2, C3k2, [512, False]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

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

@@ -1,5 +1,8 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# RT-DETR-l object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
+# 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

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

@@ -1,5 +1,8 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# RT-DETR-ResNet101 object detection model with P3-P5 outputs.
+# 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

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

@@ -1,5 +1,8 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# RT-DETR-ResNet50 object detection model with P3-P5 outputs.
+# 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

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

@@ -1,5 +1,8 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# RT-DETR-x object detection model with P3-P5 outputs. For details see https://docs.ultralytics.com/models/rtdetr
+# 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

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)