dgenerate-ultralytics-headless 8.3.253__py3-none-any.whl

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -0,0 +1,41 @@
+# 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
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── tiger-pose ← downloads here (49.8 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: tiger-pose # dataset root dir
+train: images/train # train images (relative to 'path') 210 images
+val: images/val # val images (relative to 'path') 53 images
+
+# Keypoints
+kpt_shape: [12, 2] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+
+# Classes
+names:
+  0: tiger
+
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - head
+    - withers
+    - tail_base
+    - right_hind_hock
+    - right_hind_paw
+    - left_hind_paw
+    - left_hind_hock
+    - right_front_wrist
+    - right_front_paw
+    - left_front_wrist
+    - left_front_paw
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/tiger-pose.zip

ultralytics/cfg/datasets/xView.yaml

@@ -0,0 +1,155 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# DIUx xView 2018 Challenge dataset https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
+# --------  Download and extract data manually to `datasets/xView` before running the train command.  --------
+# Documentation: https://docs.ultralytics.com/datasets/detect/xview/
+# Example usage: yolo train data=xView.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── xView ← downloads here (20.7 GB)
+
+# 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: xView # dataset root dir
+train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
+val: images/autosplit_val.txt # val images (relative to 'path') 10% of 847 train images
+
+# Classes
+names:
+  0: Fixed-wing Aircraft
+  1: Small Aircraft
+  2: Cargo Plane
+  3: Helicopter
+  4: Passenger Vehicle
+  5: Small Car
+  6: Bus
+  7: Pickup Truck
+  8: Utility Truck
+  9: Truck
+  10: Cargo Truck
+  11: Truck w/Box
+  12: Truck Tractor
+  13: Trailer
+  14: Truck w/Flatbed
+  15: Truck w/Liquid
+  16: Crane Truck
+  17: Railway Vehicle
+  18: Passenger Car
+  19: Cargo Car
+  20: Flat Car
+  21: Tank car
+  22: Locomotive
+  23: Maritime Vessel
+  24: Motorboat
+  25: Sailboat
+  26: Tugboat
+  27: Barge
+  28: Fishing Vessel
+  29: Ferry
+  30: Yacht
+  31: Container Ship
+  32: Oil Tanker
+  33: Engineering Vehicle
+  34: Tower crane
+  35: Container Crane
+  36: Reach Stacker
+  37: Straddle Carrier
+  38: Mobile Crane
+  39: Dump Truck
+  40: Haul Truck
+  41: Scraper/Tractor
+  42: Front loader/Bulldozer
+  43: Excavator
+  44: Cement Mixer
+  45: Ground Grader
+  46: Hut/Tent
+  47: Shed
+  48: Building
+  49: Aircraft Hangar
+  50: Damaged Building
+  51: Facility
+  52: Construction Site
+  53: Vehicle Lot
+  54: Helipad
+  55: Storage Tank
+  56: Shipping container lot
+  57: Shipping Container
+  58: Pylon
+  59: Tower
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  import json
+  from pathlib import Path
+  import shutil
+
+  import numpy as np
+  from PIL import Image
+
+  from ultralytics.utils import TQDM
+  from ultralytics.data.split import autosplit
+  from ultralytics.utils.ops import xyxy2xywhn
+
+
+  def convert_labels(fname=Path("xView/xView_train.geojson")):
+      """Convert xView GeoJSON labels to YOLO format (classes 0-59) and save them as text files."""
+      path = fname.parent
+      with open(fname, encoding="utf-8") as f:
+          print(f"Loading {fname}...")
+          data = json.load(f)
+
+      # Make dirs
+      labels = path / "labels" / "train"
+      shutil.rmtree(labels, ignore_errors=True)
+      labels.mkdir(parents=True, exist_ok=True)
+
+      # xView classes 11-94 to 0-59
+      xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
+                           12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
+                           29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
+                           47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]
+
+      shapes = {}
+      for feature in TQDM(data["features"], desc=f"Converting {fname}"):
+          p = feature["properties"]
+          if p["bounds_imcoords"]:
+              image_id = p["image_id"]
+              image_file = path / "train_images" / image_id
+              if image_file.exists():  # 1395.tif missing
+                  try:
+                      box = np.array([int(num) for num in p["bounds_imcoords"].split(",")])
+                      assert box.shape[0] == 4, f"incorrect box shape {box.shape[0]}"
+                      cls = p["type_id"]
+                      cls = xview_class2index[int(cls)]  # xView class to 0-59
+                      assert 59 >= cls >= 0, f"incorrect class index {cls}"
+
+                      # Write YOLO label
+                      if image_id not in shapes:
+                          shapes[image_id] = Image.open(image_file).size
+                      box = xyxy2xywhn(box[None].astype(float), w=shapes[image_id][0], h=shapes[image_id][1], clip=True)
+                      with open((labels / image_id).with_suffix(".txt"), "a", encoding="utf-8") as f:
+                          f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n")  # write label.txt
+                  except Exception as e:
+                      print(f"WARNING: skipping one label for {image_file}: {e}")
+
+
+  # Download manually from https://challenge.xviewdataset.org
+  dir = Path(yaml["path"])  # dataset root dir
+  # urls = [
+  #     "https://d307kc0mrhucc3.cloudfront.net/train_labels.zip",  # train labels
+  #     "https://d307kc0mrhucc3.cloudfront.net/train_images.zip",  # 15G, 847 train images
+  #     "https://d307kc0mrhucc3.cloudfront.net/val_images.zip",  # 5G, 282 val images (no labels)
+  # ]
+  # download(urls, dir=dir)
+
+  # Convert labels
+  convert_labels(dir / "xView_train.geojson")
+
+  # Move images
+  images = Path(dir / "images")
+  images.mkdir(parents=True, exist_ok=True)
+  Path(dir / "train_images").rename(dir / "images" / "train")
+  Path(dir / "val_images").rename(dir / "images" / "val")
+
+  # Split
+  autosplit(dir / "images" / "train")

ultralytics/cfg/default.yaml

@@ -0,0 +1,130 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# 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 or yolov8n.yaml
+data: # (str, optional) path to data file, i.e. coco8.yaml
+epochs: 100 # (int) number of epochs to train for
+time: # (float, optional) max hours to train; overrides epochs if set
+patience: 100 # (int) early stop after N epochs without val improvement
+batch: 16 # (int) batch size; use -1 for AutoBatch
+imgsz: 640 # (int | list) train/val use int (square); predict/export may use [h,w]
+save: True # (bool) save train checkpoints and predict results
+save_period: -1 # (int) save checkpoint every N epochs; disabled if < 1
+cache: False # (bool | str) cache images in RAM (True/'ram') or on 'disk' to speed dataloading; False disables
+device: # (int | str | list) device: 0 or [0,1,2,3] for CUDA, 'cpu'/'mps', or -1/[-1,-1] to auto-select idle GPUs
+workers: 8 # (int) dataloader workers (per RANK if DDP)
+project: # (str, optional) project name for results root
+name: # (str, optional) experiment name; results in 'project/name'
+exist_ok: False # (bool) overwrite existing 'project/name' if True
+pretrained: True # (bool | str) use pretrained weights (bool) or load weights from path (str)
+optimizer: auto # (str) optimizer: SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, or auto
+verbose: True # (bool) print verbose logs during training/val
+seed: 0 # (int) random seed for reproducibility
+deterministic: True # (bool) enable deterministic ops; reproducible but may be slower
+single_cls: False # (bool) treat all classes as a single class
+rect: False # (bool) rectangular batches for train; rectangular batching for val when mode='val'
+cos_lr: False # (bool) cosine learning rate scheduler
+close_mosaic: 10 # (int) disable mosaic augmentation for final N epochs (0 to keep enabled)
+resume: False # (bool) resume training from last checkpoint in the run dir
+amp: True # (bool) Automatic Mixed Precision (AMP) training; True runs AMP capability check
+fraction: 1.0 # (float) fraction of training dataset to use (1.0 = all)
+profile: False # (bool) profile ONNX/TensorRT speeds during training for loggers
+freeze: # (int | list, optional) freeze first N layers (int) or specific layer indices (list)
+multi_scale: False # (bool) multiscale training by varying image size
+compile: False # (bool | str) enable torch.compile() backend='inductor'; True="default", False=off, or "default|reduce-overhead|max-autotune-no-cudagraphs"
+
+# Segmentation
+overlap_mask: True # (bool) merge instance masks into one mask during training (segment only)
+mask_ratio: 4 # (int) mask downsample ratio (segment only)
+
+# Classification
+dropout: 0.0 # (float) dropout for classification head (classify only)
+
+# Val/Test settings ----------------------------------------------------------------------------------------------------
+val: True # (bool) run validation/testing during training
+split: val # (str) dataset split to evaluate: 'val', 'test' or 'train'
+save_json: False # (bool) save results to COCO JSON for external evaluation
+conf: # (float, optional) confidence threshold; defaults: predict=0.25, val=0.001
+iou: 0.7 # (float) IoU threshold used for NMS
+max_det: 300 # (int) maximum number of detections per image
+half: False # (bool) use half precision (FP16) if supported
+dnn: False # (bool) use OpenCV DNN for ONNX inference
+plots: True # (bool) save plots and images during train/val
+
+# Predict settings -----------------------------------------------------------------------------------------------------
+source: # (str, optional) path/dir/URL/stream for images or videos; e.g. 'ultralytics/assets' or '0' for webcam
+vid_stride: 1 # (int) read every Nth frame for video sources
+stream_buffer: False # (bool) True buffers all frames; False keeps the most recent frame for low-latency streams
+visualize: False # (bool) visualize model features (predict) or TP/FP/FN confusion (val)
+augment: False # (bool) apply test-time augmentation during prediction
+agnostic_nms: False # (bool) class-agnostic NMS
+classes: # (int | list[int], optional) filter by class id(s), e.g. 0 or [0,2,3]
+retina_masks: False # (bool) use high-resolution segmentation masks (segment)
+embed: # (list[int], optional) return feature embeddings from given layer indices
+
+# Visualize settings ---------------------------------------------------------------------------------------------------
+show: False # (bool) show images/videos in a window if supported
+save_frames: False # (bool) save individual frames from video predictions
+save_txt: False # (bool) save results as .txt files (xywh format)
+save_conf: False # (bool) save confidence scores with results
+save_crop: False # (bool) save cropped prediction regions to files
+show_labels: True # (bool) draw class labels on images, e.g. 'person'
+show_conf: True # (bool) draw confidence values on images, e.g. '0.99'
+show_boxes: True # (bool) draw bounding boxes on images
+line_width: # (int, optional) line width of boxes; auto-scales with image size if not set
+
+# Export settings ------------------------------------------------------------------------------------------------------
+format: torchscript # (str) target format, e.g. torchscript|onnx|openvino|engine|coreml|saved_model|pb|tflite|edgetpu|tfjs|paddle|mnn|ncnn|imx|rknn|executorch
+keras: False # (bool) TF SavedModel only (format=saved_model); enable Keras layers during export
+optimize: False # (bool) TorchScript only; apply mobile optimizations to the scripted model
+int8: False # (bool) INT8/PTQ where supported (openvino, tflite, tfjs, engine, imx); needs calibration data/fraction
+dynamic: False # (bool) dynamic shapes for torchscript, onnx, openvino, engine; enable variable image sizes
+simplify: True # (bool) ONNX/engine only; run graph simplifier for cleaner ONNX before runtime conversion
+opset: # (int, optional) ONNX/engine only; opset version for export; leave unset to use a tested default
+workspace: # (float, optional) engine (TensorRT) only; workspace size in GiB, e.g. 4
+nms: False # (bool) fuse NMS into exported model when backend supports; if True, conf/iou apply (agnostic_nms except coreml)
+
+# Hyperparameters ------------------------------------------------------------------------------------------------------
+lr0: 0.01 # (float) initial learning rate (SGD=1e-2, Adam/AdamW=1e-3)
+lrf: 0.01 # (float) final LR fraction; final LR = lr0 * lrf
+momentum: 0.937 # (float) SGD momentum or Adam beta1
+weight_decay: 0.0005 # (float) weight decay (L2 regularization)
+warmup_epochs: 3.0 # (float) warmup epochs (fractions allowed)
+warmup_momentum: 0.8 # (float) initial momentum during warmup
+warmup_bias_lr: 0.1 # (float) bias learning rate during warmup
+box: 7.5 # (float) box loss gain
+cls: 0.5 # (float) classification loss gain
+dfl: 1.5 # (float) distribution focal loss gain
+pose: 12.0 # (float) pose loss gain (pose tasks)
+kobj: 1.0 # (float) keypoint objectness loss gain (pose tasks)
+nbs: 64 # (int) nominal batch size used for loss normalization
+hsv_h: 0.015 # (float) HSV hue augmentation fraction
+hsv_s: 0.7 # (float) HSV saturation augmentation fraction
+hsv_v: 0.4 # (float) HSV value (brightness) augmentation fraction
+degrees: 0.0 # (float) rotation degrees (+/-)
+translate: 0.1 # (float) translation fraction (+/-)
+scale: 0.5 # (float) scale gain (+/-)
+shear: 0.0 # (float) shear degrees (+/-)
+perspective: 0.0 # (float) perspective fraction (0–0.001 typical)
+flipud: 0.0 # (float) vertical flip probability
+fliplr: 0.5 # (float) horizontal flip probability
+bgr: 0.0 # (float) RGB↔BGR channel swap probability
+mosaic: 1.0 # (float) mosaic augmentation probability
+mixup: 0.0 # (float) MixUp augmentation probability
+cutmix: 0.0 # (float) CutMix augmentation probability
+copy_paste: 0.0 # (float) segmentation copy-paste probability
+copy_paste_mode: flip # (str) copy-paste strategy for segmentation: flip or mixup
+auto_augment: randaugment # (str) classification auto augmentation policy: randaugment, autoaugment, augmix
+erasing: 0.4 # (float) random erasing probability for classification (0–0.9), <1.0
+
+# Custom config.yaml ---------------------------------------------------------------------------------------------------
+cfg: # (str, optional) path to a config.yaml that overrides defaults
+
+# Tracker settings ------------------------------------------------------------------------------------------------------
+tracker: botsort.yaml # (str) tracker config file: botsort.yaml or bytetrack.yaml

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

@@ -0,0 +1,17 @@
+# 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: 1000 # number of classes
+
+# 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: 1000 # 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: 86 layers, 1633584 parameters, 1633584 gradients, 0.5 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 86 layers, 5545488 parameters, 5545488 gradients, 1.6 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 106 layers, 10455696 parameters, 10455696 gradients, 5.0 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 176 layers, 12937104 parameters, 12937104 gradients, 6.2 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 176 layers, 28458544 parameters, 28458544 gradients, 13.7 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: 196 layers, 2695747 parameters, 2695731 gradients, 6.9 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 196 layers, 9744931 parameters, 9744915 gradients, 22.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 246 layers, 20963523 parameters, 20963507 gradients, 72.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 372 layers, 26220995 parameters, 26220979 gradients, 91.3 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 372 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-pose.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.50, 0.25, 1024] # summary: 196 layers, 2908507 parameters, 2908491 gradients, 7.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 196 layers, 9948811 parameters, 9948795 gradients, 23.5 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 246 layers, 20973273 parameters, 20973257 gradients, 72.3 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 372 layers, 26230745 parameters, 26230729 gradients, 91.4 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 372 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: 203 layers, 2876848 parameters, 2876832 gradients, 10.5 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 203 layers, 10113248 parameters, 10113232 gradients, 35.8 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 253 layers, 22420896 parameters, 22420880 gradients, 123.9 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 379 layers, 27678368 parameters, 27678352 gradients, 143.0 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 379 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: 181 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 181 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 231 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 357 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 357 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/11/yoloe-11-seg.yaml

@@ -0,0 +1,48 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Ultralytics YOLOE-11-seg instance segmentation model. For usage examples, see https://docs.ultralytics.com/tasks/segment
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yoloe-11n-seg.yaml' will call yoloe-11-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, YOLOESegment, [nc, 32, 256, 512, True]] # Detect(P3, P4, P5)