dgenerate-ultralytics-headless 8.3.196__py3-none-any.whl → 8.3.248__py3-none-any.whl

ultralytics/cfg/datasets/coco128-seg.yaml

@@ -2,7 +2,7 @@
 
 # COCO128-seg dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/segment/coco/
-# Example usage: yolo train data=coco128.yaml
+# Example usage: yolo train data=coco128-seg.yaml
 # parent
 # ├── ultralytics
 # └── datasets

ultralytics/cfg/datasets/coco8-pose.yaml

@@ -22,5 +22,26 @@ flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 names:
   0: person
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-pose.zip

ultralytics/cfg/datasets/construction-ppe.yaml

@@ -0,0 +1,32 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# Construction-PPE dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/construction-ppe/
+# Example usage: yolo train data=construction-ppe.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── construction-ppe ← downloads here (178.4 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: construction-ppe # dataset root dir
+train: images/train # train images (relative to 'path') 1132 images
+val: images/val # val images (relative to 'path') 143 images
+test: images/test # test images (relative to 'path') 141 images
+
+# Classes
+names:
+  0: helmet
+  1: gloves
+  2: vest
+  3: boots
+  4: goggles
+  5: none
+  6: Person
+  7: no_helmet
+  8: no_goggle
+  9: no_gloves
+  10: no_boots
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/construction-ppe.zip

ultralytics/cfg/datasets/dog-pose.yaml

@@ -20,5 +20,33 @@ kpt_shape: [24, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y
 names:
   0: dog
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - front_left_paw
+    - front_left_knee
+    - front_left_elbow
+    - rear_left_paw
+    - rear_left_knee
+    - rear_left_elbow
+    - front_right_paw
+    - front_right_knee
+    - front_right_elbow
+    - rear_right_paw
+    - rear_right_knee
+    - rear_right_elbow
+    - tail_start
+    - tail_end
+    - left_ear_base
+    - right_ear_base
+    - nose
+    - chin
+    - left_ear_tip
+    - right_ear_tip
+    - left_eye
+    - right_eye
+    - withers
+    - throat
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dog-pose.zip

ultralytics/cfg/datasets/dota8-multispectral.yaml

@@ -6,7 +6,7 @@
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota8-multispectral ← downloads here (37.3MB)
+#     └── dota8-multispectral ← downloads here (37.3 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: dota8-multispectral # dataset root dir

ultralytics/cfg/datasets/dota8.yaml

@@ -1,12 +1,12 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# DOTA8 dataset 8 images from split DOTAv1 dataset by Ultralytics
+# DOTA8 dataset (8 images from the DOTAv1 split) by Ultralytics
 # Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
 # Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
 # parent
 # ├── ultralytics
 # └── datasets
-#     └── dota8 ← downloads here (1MB)
+#     └── dota8 ← downloads here (1 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: dota8 # dataset root dir

ultralytics/cfg/datasets/hand-keypoints.yaml

@@ -15,12 +15,36 @@ val: images/val # val images (relative to 'path') 7992 images
 
 # Keypoints
 kpt_shape: [21, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
-flip_idx:
-  [0, 1, 2, 4, 3, 10, 11, 12, 13, 14, 5, 6, 7, 8, 9, 15, 16, 17, 18, 19, 20]
+flip_idx: [0, 1, 2, 4, 3, 10, 11, 12, 13, 14, 5, 6, 7, 8, 9, 15, 16, 17, 18, 19, 20]
 
 # Classes
 names:
   0: hand
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - wrist
+    - thumb_cmc
+    - thumb_mcp
+    - thumb_ip
+    - thumb_tip
+    - index_mcp
+    - index_pip
+    - index_dip
+    - index_tip
+    - middle_mcp
+    - middle_pip
+    - middle_dip
+    - middle_tip
+    - ring_mcp
+    - ring_pip
+    - ring_dip
+    - ring_tip
+    - pinky_mcp
+    - pinky_pip
+    - pinky_dip
+    - pinky_tip
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/hand-keypoints.zip

ultralytics/cfg/datasets/kitti.yaml

@@ -0,0 +1,27 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+# KITTI dataset by Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago
+# Documentation: https://docs.ultralytics.com/datasets/detect/kitti/
+# Example usage: yolo train data=kitti.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── kitti ← downloads here (390.5 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: kitti # dataset root dir
+train: images/train # train images (relative to 'path') 5985 images
+val: images/val # val images (relative to 'path') 1496 images
+
+names:
+  0: car
+  1: van
+  2: truck
+  3: pedestrian
+  4: person_sitting
+  5: cyclist
+  6: tram
+  7: misc
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/kitti.zip

ultralytics/cfg/datasets/lvis.yaml

@@ -35,7 +35,7 @@ names:
   17: armband
   18: armchair
   19: armoire
-  20: armor/armour
+  20: armor
   21: artichoke
   22: trash can/garbage can/wastebin/dustbin/trash barrel/trash bin
   23: ashtray
@@ -245,7 +245,7 @@ names:
   227: CD player
   228: celery
   229: cellular telephone/cellular phone/cellphone/mobile phone/smart phone
-  230: chain mail/ring mail/chain armor/chain armour/ring armor/ring armour
+  230: chain mail/ring mail/chain armor/ring armor
   231: chair
   232: chaise longue/chaise/daybed
   233: chalice
@@ -305,7 +305,7 @@ names:
   287: coin
   288: colander/cullender
   289: coleslaw/slaw
-  290: coloring material/colouring material
+  290: coloring material
   291: combination lock
   292: pacifier/teething ring
   293: comic book
@@ -401,7 +401,7 @@ names:
   383: domestic ass/donkey
   384: doorknob/doorhandle
   385: doormat/welcome mat
-  386: doughnut/donut
+  386: donut
   387: dove
   388: dragonfly
   389: drawer
@@ -1072,7 +1072,7 @@ names:
   1054: tag
   1055: taillight/rear light
   1056: tambourine
-  1057: army tank/armored combat vehicle/armoured combat vehicle
+  1057: army tank/armored combat vehicle
   1058: tank/tank storage vessel/storage tank
   1059: tank top/tank top clothing
   1060: tape/tape sticky cloth or paper
@@ -1223,12 +1223,12 @@ names:
 download: |
   from pathlib import Path
 
+  from ultralytics.utils import ASSETS_URL
   from ultralytics.utils.downloads import download
 
   # Download labels
   dir = Path(yaml["path"])  # dataset root dir
-  url = "https://github.com/ultralytics/assets/releases/download/v0.0.0/"
-  urls = [f"{url}lvis-labels-segments.zip"]
+  urls = [f"{ASSETS_URL}/lvis-labels-segments.zip"]
   download(urls, dir=dir.parent)
 
   # Download data

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

@@ -182,7 +182,7 @@ names:
   163: Dolphin
   164: Door
   165: Door handle
-  166: Doughnut
+  166: Donut
   167: Dragonfly
   168: Drawer
   169: Dress

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -21,5 +21,21 @@ flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
 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

@@ -1,7 +1,7 @@
 # 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!  --------
+# 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
@@ -12,7 +12,7 @@
 # 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 # train images (relative to 'path') 10% of 847 train images
+val: images/autosplit_val.txt # val images (relative to 'path') 10% of 847 train images
 
 # Classes
 names:
@@ -80,8 +80,8 @@ names:
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json
-  import os
   from pathlib import Path
+  import shutil
 
   import numpy as np
   from PIL import Image
@@ -92,15 +92,15 @@ download: |
 
 
   def convert_labels(fname=Path("xView/xView_train.geojson")):
-      """Converts xView geoJSON labels to YOLO format, mapping classes to indices 0-59 and saving as text files."""
+      """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(path / "labels" / "train")
-      os.system(f"rm -rf {labels}")
+      labels = path / "labels" / "train"
+      shutil.rmtree(labels, ignore_errors=True)
       labels.mkdir(parents=True, exist_ok=True)
 
       # xView classes 11-94 to 0-59
@@ -113,24 +113,24 @@ download: |
       for feature in TQDM(data["features"], desc=f"Converting {fname}"):
           p = feature["properties"]
           if p["bounds_imcoords"]:
-              id = p["image_id"]
-              file = path / "train_images" / id
-              if file.exists():  # 1395.tif missing
+              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 0-60
+                      cls = xview_class2index[int(cls)]  # xView class to 0-59
                       assert 59 >= cls >= 0, f"incorrect class index {cls}"
 
                       # Write YOLO label
-                      if id not in shapes:
-                          shapes[id] = Image.open(file).size
-                      box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
-                      with open((labels / id).with_suffix(".txt"), "a", encoding="utf-8") as f:
+                      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 {file}: {e}")
+                      print(f"WARNING: skipping one label for {image_file}: {e}")
 
 
   # Download manually from https://challenge.xviewdataset.org

ultralytics/cfg/default.yaml

@@ -7,122 +7,124 @@ 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
+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) 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[h,w] for predict and export modes
+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 x epochs (disabled if < 1)
-cache: False # (bool) True/ram, disk or False. Use cache for data loading
-device: # (int | str | list) device: CUDA device=0 or [0,1,2,3] or "cpu/mps" or -1 or [-1,-1] to auto-select idle GPUs
-workers: 8 # (int) number of worker threads for data loading (per RANK if DDP)
-project: # (str, optional) project name
-name: # (str, optional) experiment name, results saved to 'project/name' directory
-exist_ok: False # (bool) whether to overwrite existing experiment
-pretrained: True # (bool | str) whether to use a pretrained model (bool) or a model to load weights from (str)
-optimizer: auto # (str) optimizer to use, choices=[SGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, auto]
-verbose: True # (bool) whether to print verbose output
+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) whether to enable deterministic mode
-single_cls: False # (bool) train multi-class data as single-class
-rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
-cos_lr: False # (bool) use cosine learning rate scheduler
-close_mosaic: 10 # (int) disable mosaic augmentation for final epochs (0 to disable)
-resume: False # (bool) resume training from last checkpoint
-amp: True # (bool) Automatic Mixed Precision (AMP) training, choices=[True, False], True runs AMP check
-fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)
-profile: False # (bool) profile ONNX and TensorRT speeds during training for loggers
-freeze: # (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
-compile: False # (bool) Run torch.compile() on the model before train/val/predict
+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 object masks into a single image mask during training (segment train only)
-mask_ratio: 4 # (int) mask downsample ratio (segment train only)
+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) use dropout regularization (classify train only)
+dropout: 0.0 # (float) dropout for classification head (classify only)
 
 # Val/Test settings ----------------------------------------------------------------------------------------------------
-val: True # (bool) validate/test during training
-split: val # (str) dataset split to use for validation, i.e. 'val', 'test' or 'train'
-save_json: False # (bool) save results to JSON file
-conf: # (float, optional) object confidence threshold for detection (default 0.25 predict, 0.001 val)
-iou: 0.7 # (float) intersection over union (IoU) threshold for NMS
+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)
+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) source directory for images or videos
-vid_stride: 1 # (int) video frame-rate stride
-stream_buffer: False # (bool) buffer all streaming frames (True) or return the most recent frame (False)
-visualize: False # (bool) visualize model features (predict) or visualize TP, FP, FN (val)
-augment: False # (bool) apply image augmentation to prediction sources
+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 results by class, i.e. classes=0, or classes=[0,2,3]
-retina_masks: False # (bool) use high-resolution segmentation masks
-embed: # (list[int], optional) return feature vectors/embeddings from given layers
+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 predicted images and videos if environment allows
-save_frames: False # (bool) save predicted individual video frames
-save_txt: False # (bool) save results as .txt file
-save_conf: False # (bool) save results with confidence scores
-save_crop: False # (bool) save cropped images with results
-show_labels: True # (bool) show prediction labels, i.e. 'person'
-show_conf: True # (bool) show prediction confidence, i.e. '0.99'
-show_boxes: True # (bool) show prediction boxes
-line_width: # (int, optional) line width of the bounding boxes. Scaled to image size if None.
+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) format to export to, choices at https://docs.ultralytics.com/modes/export/#export-formats
-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: True # (bool) ONNX: simplify model using `onnxslim`
-opset: # (int, optional) ONNX: opset version
-workspace: # (float, optional) TensorRT: workspace size (GiB), `None` will let TensorRT auto-allocate memory
-nms: False # (bool) CoreML: add NMS
+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 (i.e. SGD=1E-2, Adam=1E-3)
-lrf: 0.01 # (float) final learning rate (lr0 * lrf)
-momentum: 0.937 # (float) SGD momentum/Adam beta1
-weight_decay: 0.0005 # (float) optimizer weight decay 5e-4
-warmup_epochs: 3.0 # (float) warmup epochs (fractions ok)
-warmup_momentum: 0.8 # (float) warmup initial momentum
-warmup_bias_lr: 0.1 # (float) warmup initial bias lr
+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) 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
-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)
-hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
-degrees: 0.0 # (float) image rotation (+/- deg)
-translate: 0.1 # (float) image translation (+/- fraction)
-scale: 0.5 # (float) image scale (+/- gain)
-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)
-cutmix: 0.0 # (float) image cutmix (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 (0-0.9), 0 means no erasing, must be less than 1.0.
+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) for overriding defaults.yaml
+cfg: # (str, optional) path to a config.yaml that overrides defaults
 
 # Tracker settings ------------------------------------------------------------------------------------------------------
-tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]
+tracker: botsort.yaml # (str) tracker config file: botsort.yaml or bytetrack.yaml

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

@@ -7,7 +7,7 @@
 # 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'
+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

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

@@ -1,10 +1,10 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# YOLO11-seg instance segmentation model. For Usage examples see https://docs.ultralytics.com/tasks/segment
+# 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=yolo11n-seg.yaml' will call yolo11-seg.yaml with scale 'n'
+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

ultralytics/cfg/models/11/yoloe-11.yaml

@@ -1,10 +1,10 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
+# Ultralytics YOLOE-11 object detection model with P3/8 - P5/32 outputs. For usage examples, see 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'
+scales: # model compound scaling constants, i.e. 'model=yoloe-11n.yaml' will call yoloe-11.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