ultralytics 8.0.235 YOLOv8 OBB train, val, predict and export (#4499)

Co-authored-by: Yash Khurana <ykhurana6@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Swamita Gupta <swamita2001@gmail.com>
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
Co-authored-by: Laughing-q <1182102784@qq.com>

ultralytics/cfg/__init__.py

@@ -13,18 +13,25 @@ from ultralytics.utils import (ASSETS, DEFAULT_CFG, DEFAULT_CFG_DICT, DEFAULT_CF
 
 # Define valid tasks and modes
 MODES = 'train', 'val', 'predict', 'export', 'track', 'benchmark'
-TASKS = 'detect', 'segment', 'classify', 'pose'
-TASK2DATA = {'detect': 'coco8.yaml', 'segment': 'coco8-seg.yaml', 'classify': 'imagenet10', 'pose': 'coco8-pose.yaml'}
+TASKS = 'detect', 'segment', 'classify', 'pose', 'obb'
+TASK2DATA = {
+    'detect': 'coco8.yaml',
+    'segment': 'coco8-seg.yaml',
+    'classify': 'imagenet10',
+    'pose': 'coco8-pose.yaml',
+    'obb': 'dota8-obb.yaml'}  # not implemented yet
 TASK2MODEL = {
     'detect': 'yolov8n.pt',
     'segment': 'yolov8n-seg.pt',
     'classify': 'yolov8n-cls.pt',
-    'pose': 'yolov8n-pose.pt'}
+    'pose': 'yolov8n-pose.pt',
+    'obb': 'yolov8n-obb.pt'}
 TASK2METRIC = {
     'detect': 'metrics/mAP50-95(B)',
     'segment': 'metrics/mAP50-95(M)',
     'classify': 'metrics/accuracy_top1',
-    'pose': 'metrics/mAP50-95(P)'}
+    'pose': 'metrics/mAP50-95(P)',
+    'obb': 'metrics/mAP50-95(OBB)'}
 
 CLI_HELP_MSG = \
     f"""
@@ -72,7 +79,7 @@ CFG_INT_KEYS = ('epochs', 'patience', 'batch', 'workers', 'seed', 'close_mosaic'
 CFG_BOOL_KEYS = ('save', 'exist_ok', 'verbose', 'deterministic', 'single_cls', 'rect', 'cos_lr', 'overlap_mask', 'val',
                  'save_json', 'save_hybrid', 'half', 'dnn', 'plots', 'show', 'save_txt', 'save_conf', 'save_crop',
                  'save_frames', 'show_labels', 'show_conf', 'visualize', 'augment', 'agnostic_nms', 'retina_masks',
-                 'show_boxes', 'keras', 'optimize', 'int8', 'dynamic', 'simplify', 'nms', 'profile')
+                 'show_boxes', 'keras', 'optimize', 'int8', 'dynamic', 'simplify', 'nms', 'profile', 'multi_scale')
 
 
 def cfg2dict(cfg):

ultralytics/cfg/datasets/DOTAv1.5.yaml

@@ -1,5 +1,5 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
-# DOTA 2.0 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
+# DOTA 1.5 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
 # Example usage: yolo train model=yolov8n-obb.pt data=DOTAv2.yaml
 # parent
 # ├── ultralytics
@@ -7,12 +7,12 @@
 #     └── dota2  ← 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/DOTAv2  # dataset root dir
+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 2.0
+# Classes for DOTA 1.5
 names:
   0: plane
   1: ship
@@ -30,8 +30,6 @@ names:
   13: soccer ball field
   14: swimming pool
   15: container crane
-  16: airport
-  17: helipad
 
 # Download script/URL (optional)
-download: https://github.com/ultralytics/yolov5/releases/download/v1.0/DOTAv2.zip
+download: https://github.com/ultralytics/yolov5/releases/download/v1.0/DOTAv1.5.zip

ultralytics/cfg/datasets/DOTAv1.yaml

@@ -0,0 +1,34 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# DOTA 1.0 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
+# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv2.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── dota2  ← 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
+
+# Classes for DOTA 1.0
+names:
+  0: plane
+  1: ship
+  2: storage tank
+  3: baseball diamond
+  4: tennis court
+  5: basketball court
+  6: ground track field
+  7: harbor
+  8: bridge
+  9: large vehicle
+  10: small vehicle
+  11: helicopter
+  12: roundabout
+  13: soccer ball field
+  14: swimming pool
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/yolov5/releases/download/v1.0/DOTAv1.zip

ultralytics/cfg/default.yaml

@@ -34,6 +34,7 @@ amp: True  # (bool) Automatic Mixed Precision (AMP) training, choices=[True, Fal
 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)

ultralytics/cfg/models/v8/yolov8-obb.yaml

@@ -0,0 +1,46 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv8 Oriented Bounding Boxes (OBB) model with P3-P5 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=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
+  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
+  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
+  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
+  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
+
+# YOLOv8.0n backbone
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]]  # 9
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
+  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
+  - [-1, 3, C2f, [512]]  # 12
+
+  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
+  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
+  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 12], 1, Concat, [1]]  # cat head P4
+  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)
+
+  - [-1, 1, Conv, [512, 3, 2]]
+  - [[-1, 9], 1, Concat, [1]]  # cat head P5
+  - [-1, 3, C2f, [1024]]  # 21 (P5/32-large)
+
+  - [[15, 18, 21], 1, OBB, [nc, 1]]  # OBB(P3, P4, P5)