ultralytics 8.1.2__tar.gz → 8.1.3__tar.gz

{ultralytics-8.1.2/ultralytics.egg-info → ultralytics-8.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.1.2
+Version: 8.1.3
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.1.2"
+__version__ = "8.1.3"
 
 from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import RTDETR, SAM, YOLO

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/Argoverse.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── Argoverse  ← downloads here (31.5 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: ../datasets/Argoverse  # dataset root dir
-train: Argoverse-1.1/images/train/  # train images (relative to 'path') 39384 images
-val: Argoverse-1.1/images/val/  # val images (relative to 'path') 15062 images
-test: Argoverse-1.1/images/test/  # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
+path: ../datasets/Argoverse # dataset root dir
+train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
+val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
+test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
 
 # Classes
 names:
@@ -25,7 +24,6 @@ names:
   6: traffic_light
   7: stop_sign
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/DOTAv1.5.yaml

@@ -8,10 +8,10 @@
 #     └── dota1.5  ← downloads here (2GB)
 
 # 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/DOTAv1.5  # dataset root dir
-train: images/train  # train images (relative to 'path') 1411 images
-val: images/val  # val images (relative to 'path') 458 images
-test: images/test  # test images (optional) 937 images
+path: ../datasets/DOTAv1.5 # dataset root dir
+train: images/train # train images (relative to 'path') 1411 images
+val: images/val # val images (relative to 'path') 458 images
+test: images/test # test images (optional) 937 images
 
 # Classes for DOTA 1.5
 names:

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/DOTAv1.yaml

@@ -8,10 +8,10 @@
 #     └── dota1  ← downloads here (2GB)
 
 # 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/DOTAv1  # dataset root dir
-train: images/train  # train images (relative to 'path') 1411 images
-val: images/val  # val images (relative to 'path') 458 images
-test: images/test  # test images (optional) 937 images
+path: ../datasets/DOTAv1 # dataset root dir
+train: images/train # train images (relative to 'path') 1411 images
+val: images/val # val images (relative to 'path') 458 images
+test: images/test # test images (optional) 937 images
 
 # Classes for DOTA 1.0
 names:

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/GlobalWheat2020.yaml

@@ -7,9 +7,8 @@
 # └── datasets
 #     └── GlobalWheat2020  ← downloads here (7.0 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: ../datasets/GlobalWheat2020  # dataset root dir
+path: ../datasets/GlobalWheat2020 # dataset root dir
 train: # train images (relative to 'path') 3422 images
   - images/arvalis_1
   - images/arvalis_2
@@ -30,7 +29,6 @@ test: # test images (optional) 1276 images
 names:
   0: wheat_head
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from ultralytics.utils.downloads import download

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/ImageNet.yaml

@@ -8,12 +8,11 @@
 # └── datasets
 #     └── imagenet  ← downloads here (144 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: ../datasets/imagenet  # dataset root dir
-train: train  # train images (relative to 'path') 1281167 images
-val: val  # val images (relative to 'path') 50000 images
-test:  # test images (optional)
+path: ../datasets/imagenet # dataset root dir
+train: train # train images (relative to 'path') 1281167 images
+val: val # val images (relative to 'path') 50000 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -2021,6 +2020,5 @@ map:
   n13133613: ear
   n15075141: toilet_tissue
 
-
 # Download script/URL (optional)
 download: yolo/data/scripts/get_imagenet.sh

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/Objects365.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── Objects365  ← downloads here (712 GB = 367G data + 345G zips)
 
-
 # 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/Objects365  # dataset root dir
-train: images/train  # train images (relative to 'path') 1742289 images
+path: ../datasets/Objects365 # dataset root dir
+train: images/train # train images (relative to 'path') 1742289 images
 val: images/val # val images (relative to 'path') 80000 images
-test:  # test images (optional)
+test: # test images (optional)
 
 # Classes
 names:
@@ -382,7 +381,6 @@ names:
   363: Curling
   364: Table Tennis
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from tqdm import tqdm

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/SKU-110K.yaml

@@ -7,18 +7,16 @@
 # └── datasets
 #     └── SKU-110K  ← downloads here (13.6 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: ../datasets/SKU-110K  # dataset root dir
-train: train.txt  # train images (relative to 'path')  8219 images
-val: val.txt  # val images (relative to 'path')  588 images
-test: test.txt  # test images (optional)  2936 images
+path: ../datasets/SKU-110K # dataset root dir
+train: train.txt # train images (relative to 'path')  8219 images
+val: val.txt # val images (relative to 'path')  588 images
+test: test.txt # test images (optional)  2936 images
 
 # Classes
 names:
   0: object
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import shutil

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/VOC.yaml

@@ -7,7 +7,6 @@
 # └── datasets
 #     └── VOC  ← downloads here (2.8 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: ../datasets/VOC
 train: # train images (relative to 'path')  16551 images
@@ -43,7 +42,6 @@ names:
   18: train
   19: tvmonitor
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import xml.etree.ElementTree as ET

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/VisDrone.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── VisDrone  ← downloads here (2.3 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: ../datasets/VisDrone  # dataset root dir
-train: VisDrone2019-DET-train/images  # train images (relative to 'path')  6471 images
-val: VisDrone2019-DET-val/images  # val images (relative to 'path')  548 images
-test: VisDrone2019-DET-test-dev/images  # test images (optional)  1610 images
+path: ../datasets/VisDrone # dataset root dir
+train: VisDrone2019-DET-train/images # train images (relative to 'path')  6471 images
+val: VisDrone2019-DET-val/images # val images (relative to 'path')  548 images
+test: VisDrone2019-DET-test-dev/images # test images (optional)  1610 images
 
 # Classes
 names:
@@ -27,7 +26,6 @@ names:
   8: bus
   9: motor
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import os

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco-pose.yaml

@@ -7,15 +7,14 @@
 # └── datasets
 #     └── coco-pose  ← downloads here (20.1 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: ../datasets/coco-pose  # dataset root dir
-train: train2017.txt  # train images (relative to 'path') 118287 images
-val: val2017.txt  # val images (relative to 'path') 5000 images
-test: test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+path: ../datasets/coco-pose # dataset root dir
+train: train2017.txt # train images (relative to 'path') 118287 images
+val: val2017.txt # val images (relative to 'path') 5000 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
 
 # Keypoints
-kpt_shape: [17, 3]  # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
 flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 
 # Classes

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── coco  ← downloads here (20.1 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: ../datasets/coco  # dataset root dir
-train: train2017.txt  # train images (relative to 'path') 118287 images
-val: val2017.txt  # val images (relative to 'path') 5000 images
-test: test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+path: ../datasets/coco # dataset root dir
+train: train2017.txt # train images (relative to 'path') 118287 images
+val: val2017.txt # val images (relative to 'path') 5000 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
 
 # Classes
 names:
@@ -97,7 +96,6 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: |
   from ultralytics.utils.downloads import download

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco128-seg.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── coco128-seg  ← downloads here (7 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/coco128-seg  # dataset root dir
-train: images/train2017  # train images (relative to 'path') 128 images
-val: images/train2017  # val images (relative to 'path') 128 images
-test:  # test images (optional)
+path: ../datasets/coco128-seg # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -97,6 +96,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco128-seg.zip

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco128.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── coco128  ← downloads here (7 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/coco128  # dataset root dir
-train: images/train2017  # train images (relative to 'path') 128 images
-val: images/train2017  # val images (relative to 'path') 128 images
-test:  # test images (optional)
+path: ../datasets/coco128 # dataset root dir
+train: images/train2017 # train images (relative to 'path') 128 images
+val: images/train2017 # val images (relative to 'path') 128 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -97,6 +96,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco128.zip

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco8-pose.yaml

@@ -7,15 +7,14 @@
 # └── datasets
 #     └── coco8-pose  ← 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: ../datasets/coco8-pose  # dataset root dir
-train: images/train  # train images (relative to 'path') 4 images
-val: images/val  # val images (relative to 'path') 4 images
-test:  # test images (optional)
+path: ../datasets/coco8-pose # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
 
 # Keypoints
-kpt_shape: [17, 3]  # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
+kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
 flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 
 # Classes

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco8-seg.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── coco8-seg  ← 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: ../datasets/coco8-seg  # dataset root dir
-train: images/train  # train images (relative to 'path') 4 images
-val: images/val  # val images (relative to 'path') 4 images
-test:  # test images (optional)
+path: ../datasets/coco8-seg # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -97,6 +96,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco8-seg.zip

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/coco8.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── coco8  ← 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: ../datasets/coco8  # dataset root dir
-train: images/train  # train images (relative to 'path') 4 images
-val: images/val  # val images (relative to 'path') 4 images
-test:  # test images (optional)
+path: ../datasets/coco8 # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -97,6 +96,5 @@ names:
   78: hair drier
   79: toothbrush
 
-
 # Download script/URL (optional)
 download: https://ultralytics.com/assets/coco8.zip

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/dota8.yaml

@@ -8,9 +8,9 @@
 #     └── dota8  ← downloads here (1MB)
 
 # 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/dota8  # dataset root dir
-train: images/train  # train images (relative to 'path') 4 images
-val: images/val  # val images (relative to 'path') 4 images
+path: ../datasets/dota8 # dataset root dir
+train: images/train # train images (relative to 'path') 4 images
+val: images/val # val images (relative to 'path') 4 images
 
 # Classes for DOTA 1.0
 names:

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/open-images-v7.yaml

@@ -7,12 +7,11 @@
 # └── datasets
 #     └── open-images-v7  ← downloads here (561 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: ../datasets/open-images-v7  # dataset root dir
-train: images/train  # train images (relative to 'path') 1743042 images
-val: images/val  # val images (relative to 'path') 41620 images
-test:  # test images (optional)
+path: ../datasets/open-images-v7 # dataset root dir
+train: images/train # train images (relative to 'path') 1743042 images
+val: images/val # val images (relative to 'path') 41620 images
+test: # test images (optional)
 
 # Classes
 names:
@@ -618,7 +617,6 @@ names:
   599: Zebra
   600: Zucchini
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   from ultralytics.utils import LOGGER, SETTINGS, Path, is_ubuntu, get_ubuntu_version

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/tiger-pose.yaml

@@ -7,14 +7,13 @@
 # └── datasets
 #     └── tiger-pose  ← downloads here (75.3 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: ../datasets/tiger-pose  # dataset root dir
-train: train  # train images (relative to 'path') 210 images
-val: val  # val images (relative to 'path') 53 images
+path: ../datasets/tiger-pose # dataset root dir
+train: train # train images (relative to 'path') 210 images
+val: 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)
+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

{ultralytics-8.1.2 → ultralytics-8.1.3}/ultralytics/cfg/datasets/xView.yaml

@@ -8,11 +8,10 @@
 # └── 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: ../datasets/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
+path: ../datasets/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
 
 # Classes
 names:
@@ -77,7 +76,6 @@ names:
   58: Pylon
   59: Tower
 
-
 # Download script/URL (optional) ---------------------------------------------------------------------------------------
 download: |
   import json

ultralytics-8.1.3/ultralytics/cfg/default.yaml

@@ -0,0 +1,125 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Default training settings and hyperparameters for medium-augmentation COCO training
+
+task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
+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
+epochs: 100 # (int) number of epochs to train for
+time: # (float, optional) number of hours to train for, overrides epochs if supplied
+patience: 50 # (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
+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, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
+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
+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: None # (int | list, optional) freeze first n layers, or freeze list of layer indices during training
+multi_scale: False # (bool) Whether to use multi-scale during training
+# Segmentation
+overlap_mask: True # (bool) masks should overlap 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)
+
+# 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
+save_hybrid: False # (bool) save hybrid version of labels (labels + additional predictions)
+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
+max_det: 300 # (int) maximum number of detections per image
+half: False # (bool) use half precision (FP16)
+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
+augment: False # (bool) apply image augmentation to prediction sources
+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
+
+# 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.
+
+# 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: False # (bool) ONNX: simplify model
+opset: # (int, optional) ONNX: opset version
+workspace: 4 # (int) TensorRT: workspace size (GB)
+nms: False # (bool) CoreML: add NMS
+
+# 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
+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
+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)
+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)
+mosaic: 1.0 # (float) image mosaic (probability)
+mixup: 0.0 # (float) image mixup (probability)
+copy_paste: 0.0 # (float) segment copy-paste (probability)
+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)
+
+# Custom config.yaml ---------------------------------------------------------------------------------------------------
+cfg: # (str, optional) for overriding defaults.yaml
+
+# Tracker settings ------------------------------------------------------------------------------------------------------
+tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]

ultralytics-8.1.3/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml

@@ -0,0 +1,50 @@
+# 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
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, HGStem, [32, 48]] # 0-P2/4
+  - [-1, 6, HGBlock, [48, 128, 3]] # stage 1
+
+  - [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
+  - [-1, 6, HGBlock, [96, 512, 3]] # stage 2
+
+  - [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P3/16
+  - [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
+  - [-1, 6, HGBlock, [192, 1024, 5, True, True]]
+  - [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
+
+  - [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P4/32
+  - [-1, 6, HGBlock, [384, 2048, 5, True, False]] # stage 4
+
+head:
+  - [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
+  - [-1, 1, AIFI, [1024, 8]]
+  - [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
+  - [[-2, -1], 1, Concat, [1]]
+  - [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
+  - [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
+  - [[-2, -1], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
+
+  - [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
+  - [[-1, 17], 1, Concat, [1]] # cat Y4
+  - [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
+
+  - [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
+  - [[-1, 12], 1, Concat, [1]] # cat Y5
+  - [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
+
+  - [[21, 24, 27], 1, RTDETRDecoder, [nc]] # Detect(P3, P4, P5)