ultralytics 8.3.159__py3-none-any.whl → 8.3.161__py3-none-any.whl

tests/test_python.py

@@ -16,6 +16,7 @@ from tests import CFG, MODEL, MODELS, SOURCE, SOURCES_LIST, TASK_MODEL_DATA, TMP
 from ultralytics import RTDETR, YOLO
 from ultralytics.cfg import TASK2DATA, TASKS
 from ultralytics.data.build import load_inference_source
+from ultralytics.data.utils import check_det_dataset
 from ultralytics.utils import (
     ARM64,
     ASSETS,
@@ -720,7 +721,7 @@ def test_grayscale(task: str, model: str, data: str) -> None:
     if task == "classify":  # not support grayscale classification yet
         return
     grayscale_data = Path(TMP) / f"{Path(data).stem}-grayscale.yaml"
-    data = YAML.load(checks.check_file(data))
+    data = check_det_dataset(data)
     data["channels"] = 1  # add additional channels key for grayscale
     YAML.save(grayscale_data, data)
     # remove npy files in train/val splits if exists, might be created by previous tests

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.159"
+__version__ = "8.3.161"
 
 import os
 

ultralytics/cfg/__init__.py

@@ -954,8 +954,6 @@ def entrypoint(debug: str = "") -> None:
         from ultralytics import YOLO
 
         model = YOLO(model, task=task)
-    if isinstance(overrides.get("pretrained"), str):
-        model.load(overrides["pretrained"])
 
     # Task Update
     if task != model.task:

ultralytics/cfg/datasets/Argoverse.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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

ultralytics/cfg/datasets/DOTAv1.5.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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

ultralytics/cfg/datasets/DOTAv1.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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

ultralytics/cfg/datasets/GlobalWheat2020.yaml

@@ -9,7 +9,7 @@
 #     └── 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: GlobalWheat2020 # dataset root dir
 train: # train images (relative to 'path') 3422 images
   - images/arvalis_1
   - images/arvalis_2

ultralytics/cfg/datasets/HomeObjects-3K.yaml

@@ -9,7 +9,7 @@
 #     └── homeobjects-3K  ← downloads here (390 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/homeobjects-3K # dataset root dir
+path: homeobjects-3K # dataset root dir
 train: train/images # train images (relative to 'path') 2285 images
 val: valid/images # val images (relative to 'path') 404 images
 test: # test images (relative to 'path')

ultralytics/cfg/datasets/ImageNet.yaml

@@ -10,7 +10,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/Objects365.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/SKU-110K.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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

ultralytics/cfg/datasets/VOC.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: VOC
 train: # train images (relative to 'path')  16551 images
   - images/train2012
   - images/train2007

ultralytics/cfg/datasets/VisDrone.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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
@@ -58,8 +58,11 @@ download: |
                   cls = int(row[5]) - 1
                   box = convert_box(img_size, tuple(map(int, row[:4])))
                   lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
-                  with open(str(f).replace(f"{os.sep}annotations{os.sep}", f"{os.sep}labels{os.sep}"), "w", encoding="utf-8") as fl:
-                      fl.writelines(lines)  # write label.txt
+          
+          label_file = str(f).replace(f"{os.sep}annotations{os.sep}", f"{os.sep}labels{os.sep}")
+          with open(label_file, "w", encoding="utf-8") as fl:
+                fl.writelines(lines)
+                  
 
 
   # Download

ultralytics/cfg/datasets/african-wildlife.yaml

@@ -9,7 +9,7 @@
 #     └── african-wildlife  ← downloads here (100 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/african-wildlife # dataset root dir
+path: african-wildlife # dataset root dir
 train: train/images # train images (relative to 'path') 1052 images
 val: valid/images # val images (relative to 'path') 225 images
 test: test/images # test images (relative to 'path') 227 images

ultralytics/cfg/datasets/brain-tumor.yaml

@@ -9,7 +9,7 @@
 #     └── brain-tumor  ← downloads here (4.05 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/brain-tumor # dataset root dir
+path: brain-tumor # dataset root dir
 train: train/images # train images (relative to 'path') 893 images
 val: valid/images # val images (relative to 'path') 223 images
 test: # test images (relative to 'path')

ultralytics/cfg/datasets/carparts-seg.yaml

@@ -9,7 +9,7 @@
 #     └── carparts-seg  ← downloads here (132 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/carparts-seg # dataset root dir
+path: carparts-seg # dataset root dir
 train: train/images # train images (relative to 'path') 3516 images
 val: valid/images # val images (relative to 'path') 276 images
 test: test/images # test images (relative to 'path') 401 images

ultralytics/cfg/datasets/coco-pose.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: coco-pose # dataset root dir
 train: train2017.txt # train images (relative to 'path') 56599 images
 val: val2017.txt # val images (relative to 'path') 2346 images
 test: test-dev2017.txt # 20288 of 40670 images, submit to https://codalab.lisn.upsaclay.fr/competitions/7403

ultralytics/cfg/datasets/coco.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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

ultralytics/cfg/datasets/coco128-seg.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/coco128.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/coco8-grayscale.yaml

@@ -9,7 +9,7 @@
 #     └── coco8-grayscale  ← 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-grayscale # dataset root dir
+path: coco8-grayscale # 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)

ultralytics/cfg/datasets/coco8-multispectral.yaml

@@ -9,7 +9,7 @@
 #     └── coco8-multispectral  ← downloads here (20.2 MB)
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco8-multispectral # dataset root dir
+path: coco8-multispectral # 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)

ultralytics/cfg/datasets/coco8-pose.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/coco8-seg.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/coco8.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/crack-seg.yaml

@@ -9,7 +9,7 @@
 #     └── crack-seg  ← downloads here (91.2 MB)
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/crack-seg # dataset root dir
+path: crack-seg # dataset root dir
 train: train/images # train images (relative to 'path') 3717 images
 val: valid/images # val images (relative to 'path') 112 images
 test: test/images # test images (relative to 'path') 200 images

ultralytics/cfg/datasets/dog-pose.yaml

@@ -9,7 +9,7 @@
 #     └── dog-pose  ← downloads here (337 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/dog-pose # dataset root dir
+path: dog-pose # dataset root dir
 train: train # train images (relative to 'path') 6773 images
 val: val # val images (relative to 'path') 1703 images
 

ultralytics/cfg/datasets/dota8-multispectral.yaml

@@ -9,7 +9,7 @@
 #     └── dota8-multispectral  ← downloads here (37.3MB)
 
 # 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-multispectral # dataset root dir
+path: dota8-multispectral # dataset root dir
 train: images/train # train images (relative to 'path') 4 images
 val: images/val # val images (relative to 'path') 4 images
 

ultralytics/cfg/datasets/dota8.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: dota8 # dataset root dir
 train: images/train # train images (relative to 'path') 4 images
 val: images/val # val images (relative to 'path') 4 images
 

ultralytics/cfg/datasets/hand-keypoints.yaml

@@ -9,7 +9,7 @@
 #     └── hand-keypoints  ← downloads here (369 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/hand-keypoints # dataset root dir
+path: hand-keypoints # dataset root dir
 train: train # train images (relative to 'path') 18776 images
 val: val # val images (relative to 'path') 7992 images
 

ultralytics/cfg/datasets/lvis.yaml

@@ -9,7 +9,7 @@
 #     └── lvis  ← 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/lvis # dataset root dir
+path: lvis # dataset root dir
 train: train.txt # train images (relative to 'path') 100170 images
 val: val.txt # val images (relative to 'path') 19809 images
 minival: minival.txt # minival images (relative to 'path') 5000 images

ultralytics/cfg/datasets/medical-pills.yaml

@@ -9,7 +9,7 @@
 #     └── medical-pills  ← downloads here (8.19 MB)
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/medical-pills # dataset root dir
+path: medical-pills # dataset root dir
 train: train/images # train images (relative to 'path') 92 images
 val: valid/images # val images (relative to 'path') 23 images
 test: # test images (relative to 'path')

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

@@ -9,7 +9,7 @@
 #     └── 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
+path: 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)

ultralytics/cfg/datasets/package-seg.yaml

@@ -9,7 +9,7 @@
 #     └── package-seg  ← downloads here (102 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/package-seg # dataset root dir
+path: package-seg # dataset root dir
 train: train/images # train images (relative to 'path') 1920 images
 val: valid/images # val images (relative to 'path') 89 images
 test: test/images # test images (relative to 'path') 188 images

ultralytics/cfg/datasets/signature.yaml

@@ -9,7 +9,7 @@
 #     └── signature  ← downloads here (11.2 MB)
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/signature # dataset root dir
+path: signature # dataset root dir
 train: train/images # train images (relative to 'path') 143 images
 val: valid/images # val images (relative to 'path') 35 images
 

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -9,7 +9,7 @@
 #     └── 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
+path: tiger-pose # dataset root dir
 train: train # train images (relative to 'path') 210 images
 val: val # val images (relative to 'path') 53 images
 

ultralytics/cfg/datasets/xView.yaml

@@ -10,7 +10,7 @@
 #     └── 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
+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
 

ultralytics/data/augment.py

@@ -251,8 +251,7 @@ class Compose:
             >>> multiple_transforms = compose[0:2]  # Returns a Compose object with RandomFlip and RandomPerspective
         """
         assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
-        index = [index] if isinstance(index, int) else index
-        return Compose([self.transforms[i] for i in index])
+        return Compose([self.transforms[i] for i in index]) if isinstance(index, list) else self.transforms[index]
 
     def __setitem__(self, index: Union[list, int], value: Union[list, int]) -> None:
         """
@@ -1560,14 +1559,15 @@ class RandomFlip:
         h = 1 if instances.normalized else h
         w = 1 if instances.normalized else w
 
-        # Flip up-down
+        # WARNING: two separate if and calls to random.random() intentional for reproducibility with older versions
         if self.direction == "vertical" and random.random() < self.p:
             img = np.flipud(img)
             instances.flipud(h)
+            if self.flip_idx is not None and instances.keypoints is not None:
+                instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
         if self.direction == "horizontal" and random.random() < self.p:
             img = np.fliplr(img)
             instances.fliplr(w)
-            # For keypoints
             if self.flip_idx is not None and instances.keypoints is not None:
                 instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
         labels["img"] = np.ascontiguousarray(img)
@@ -2533,9 +2533,9 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
     flip_idx = dataset.data.get("flip_idx", [])  # for keypoints augmentation
     if dataset.use_keypoints:
         kpt_shape = dataset.data.get("kpt_shape", None)
-        if len(flip_idx) == 0 and hyp.fliplr > 0.0:
-            hyp.fliplr = 0.0
-            LOGGER.warning("No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'")
+        if len(flip_idx) == 0 and (hyp.fliplr > 0.0 or hyp.flipud > 0.0):
+            hyp.fliplr = hyp.flipud = 0.0  # both fliplr and flipud require flip_idx
+            LOGGER.warning("No 'flip_idx' array defined in data.yaml, disabling 'fliplr' and 'flipud' augmentations.")
         elif flip_idx and (len(flip_idx) != kpt_shape[0]):
             raise ValueError(f"data.yaml flip_idx={flip_idx} length must be equal to kpt_shape[0]={kpt_shape[0]}")
 
@@ -2546,7 +2546,7 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
             CutMix(dataset, pre_transform=pre_transform, p=hyp.cutmix),
             Albumentations(p=1.0),
             RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
-            RandomFlip(direction="vertical", p=hyp.flipud),
+            RandomFlip(direction="vertical", p=hyp.flipud, flip_idx=flip_idx),
             RandomFlip(direction="horizontal", p=hyp.fliplr, flip_idx=flip_idx),
         ]
     )  # transforms

ultralytics/data/converter.py

@@ -248,12 +248,10 @@ def convert_coco(
         >>> from ultralytics.data.converter import convert_coco
 
         Convert COCO annotations to YOLO format
-        >>> convert_coco("../datasets/coco/annotations/", use_segments=True, use_keypoints=False, cls91to80=False)
+        >>> convert_coco("coco/annotations/", use_segments=True, use_keypoints=False, cls91to80=False)
 
         Convert LVIS annotations to YOLO format
-        >>> convert_coco(
-        ...     "../datasets/lvis/annotations/", use_segments=True, use_keypoints=False, cls91to80=False, lvis=True
-        ... )
+        >>> convert_coco("lvis/annotations/", use_segments=True, use_keypoints=False, cls91to80=False, lvis=True)
     """
     # Create dataset directory
     save_dir = increment_path(save_dir)  # increment if save directory already exists
@@ -724,7 +722,7 @@ def convert_to_multispectral(path: Union[str, Path], n_channels: int = 10, repla
         >>> convert_to_multispectral("path/to/image.jpg", n_channels=10)
 
         Convert a dataset
-        >>> convert_to_multispectral("../datasets/coco8", n_channels=10)
+        >>> convert_to_multispectral("coco8", n_channels=10)
     """
     from scipy.interpolate import interp1d
 

ultralytics/data/dataset.py

@@ -482,7 +482,7 @@ class GroundingDataset(YOLODataset):
             a warning is logged and verification is skipped.
         """
         expected_counts = {
-            "final_mixed_train_no_coco_segm": 3662344,
+            "final_mixed_train_no_coco_segm": 3662412,
             "final_mixed_train_no_coco": 3681235,
             "final_flickr_separateGT_train_segm": 638214,
             "final_flickr_separateGT_train": 640704,

ultralytics/data/split.py

@@ -135,4 +135,4 @@ def autosplit(
 
 
 if __name__ == "__main__":
-    split_classify_dataset("../datasets/caltech101")
+    split_classify_dataset("caltech101")

ultralytics/engine/exporter.py

@@ -706,7 +706,16 @@ class Exporter:
     def export_paddle(self, prefix=colorstr("PaddlePaddle:")):
         """Export YOLO model to PaddlePaddle format."""
         assert not IS_JETSON, "Jetson Paddle exports not supported yet"
-        check_requirements(("paddlepaddle-gpu" if torch.cuda.is_available() else "paddlepaddle>=3.0.0", "x2paddle"))
+        check_requirements(
+            (
+                "paddlepaddle-gpu"
+                if torch.cuda.is_available()
+                else "paddlepaddle==3.0.0"  # pin 3.0.0 for ARM64
+                if ARM64
+                else "paddlepaddle>=3.0.0",
+                "x2paddle",
+            )
+        )
         import x2paddle  # noqa
         from x2paddle.convert import pytorch2paddle  # noqa
 
@@ -1495,7 +1504,7 @@ class NMSModel(torch.nn.Module):
         scores, classes = scores.max(dim=-1)
         self.args.max_det = min(pred.shape[1], self.args.max_det)  # in case num_anchors < max_det
         # (N, max_det, 4 coords + 1 class score + 1 class label + extra_shape).
-        out = torch.zeros(bs, self.args.max_det, boxes.shape[-1] + 2 + extra_shape, **kwargs)
+        out = torch.zeros(pred.shape[0], self.args.max_det, boxes.shape[-1] + 2 + extra_shape, **kwargs)
         for i in range(bs):
             box, cls, score, extra = boxes[i], classes[i], scores[i], extras[i]
             mask = score > self.args.conf

ultralytics/engine/model.py

@@ -777,6 +777,8 @@ class Model(torch.nn.Module):
 
         checks.check_pip_update_available()
 
+        if isinstance(kwargs.get("pretrained", None), (str, Path)):
+            self.load(kwargs["pretrained"])  # load pretrained weights if provided
         overrides = YAML.load(checks.check_yaml(kwargs["cfg"])) if kwargs.get("cfg") else self.overrides
         custom = {
             # NOTE: handle the case when 'cfg' includes 'data'.

ultralytics/engine/results.py

@@ -16,7 +16,6 @@ import torch
 from ultralytics.data.augment import LetterBox
 from ultralytics.utils import LOGGER, DataExportMixin, SimpleClass, ops
 from ultralytics.utils.plotting import Annotator, colors, save_one_box
-from ultralytics.utils.torch_utils import smart_inference_mode
 
 
 class BaseTensor(SimpleClass):
@@ -801,7 +800,7 @@ class Results(SimpleClass, DataExportMixin):
             decimals (int): Number of decimal places to round the output values to.
 
         Returns:
-            (List[Dict]): A list of dictionaries, each containing summarized information for a single detection
+            (List[Dict[str, Any]]): A list of dictionaries, each containing summarized information for a single detection
                 or classification result. The structure of each dictionary varies based on the task type
                 (classification or detection) and available information (boxes, masks, keypoints).
 
@@ -1204,7 +1203,6 @@ class Keypoints(BaseTensor):
         >>> keypoints_cpu = keypoints.cpu()  # Move keypoints to CPU
     """
 
-    @smart_inference_mode()  # avoid keypoints < conf in-place error
     def __init__(self, keypoints: Union[torch.Tensor, np.ndarray], orig_shape: Tuple[int, int]) -> None:
         """
         Initialize the Keypoints object with detection keypoints and original image dimensions.
@@ -1225,9 +1223,6 @@ class Keypoints(BaseTensor):
         """
         if keypoints.ndim == 2:
             keypoints = keypoints[None, :]
-        if keypoints.shape[2] == 3:  # x, y, conf
-            mask = keypoints[..., 2] < 0.5  # points with conf < 0.5 (not visible)
-            keypoints[..., :2][mask] = 0
         super().__init__(keypoints, orig_shape)
         self.has_visible = self.data.shape[-1] == 3