ultralytics-opencv-headless 8.4.0__tar.gz → 8.4.2__tar.gz

{ultralytics_opencv_headless-8.4.0/ultralytics_opencv_headless.egg-info → ultralytics_opencv_headless-8.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics-opencv-headless
-Version: 8.4.0
+Version: 8.4.2
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -237,11 +237,11 @@ Refer to the [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) fo
 
 | Model                                                                                        | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO26n-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-seg.pt) | 640                   | 39.6                 | 33.9                  | 53.3 ± 0.5                     | 2.1 ± 0.0                           | 2.8                | 9.1               |
-| [YOLO26s-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-seg.pt) | 640                   | 47.3                 | 40.0                  | 118.4 ± 0.9                    | 3.3 ± 0.0                           | 10.7               | 34.2              |
-| [YOLO26m-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-seg.pt) | 640                   | 52.5                 | 44.1                  | 328.2 ± 2.4                    | 6.7 ± 0.1                           | 24.8               | 121.5             |
-| [YOLO26l-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-seg.pt) | 640                   | 54.4                 | 45.5                  | 387.0 ± 3.7                    | 8.0 ± 0.1                           | 29.2               | 139.8             |
-| [YOLO26x-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-seg.pt) | 640                   | 56.5                 | 47.0                  | 787.0 ± 6.8                    | 16.4 ± 0.1                          | 65.5               | 313.5             |
+| [YOLO26n-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-seg.pt) | 640                   | 39.6                 | 33.9                  | 53.3 ± 0.5                     | 2.1 ± 0.0                           | 2.7                | 9.1               |
+| [YOLO26s-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-seg.pt) | 640                   | 47.3                 | 40.0                  | 118.4 ± 0.9                    | 3.3 ± 0.0                           | 10.4               | 34.2              |
+| [YOLO26m-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-seg.pt) | 640                   | 52.5                 | 44.1                  | 328.2 ± 2.4                    | 6.7 ± 0.1                           | 23.6               | 121.5             |
+| [YOLO26l-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-seg.pt) | 640                   | 54.4                 | 45.5                  | 387.0 ± 3.7                    | 8.0 ± 0.1                           | 28.0               | 139.8             |
+| [YOLO26x-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-seg.pt) | 640                   | 56.5                 | 47.0                  | 787.0 ± 6.8                    | 16.4 ± 0.1                          | 62.8               | 313.5             |
 
 - **mAP<sup>val</sup>** values are for single-model single-scale on the [COCO val2017](https://cocodataset.org/) dataset. See [YOLO Performance Metrics](https://docs.ultralytics.com/guides/yolo-performance-metrics/) for details. <br>Reproduce with `yolo val segment data=coco.yaml device=0`
 - **Speed** metrics are averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce with `yolo val segment data=coco.yaml batch=1 device=0|cpu`
@@ -271,11 +271,11 @@ See the [Pose Estimation Docs](https://docs.ultralytics.com/tasks/pose/) for usa
 
 | Model                                                                                          | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | ---------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO26n-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-pose.pt) | 640                   | 56.9                  | 83.0               | 40.3 ± 0.5                     | 1.8 ± 0.0                           | 2.9                | 7.5               |
-| [YOLO26s-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-pose.pt) | 640                   | 63.1                  | 86.8               | 85.3 ± 0.9                     | 2.7 ± 0.0                           | 10.4               | 23.9              |
-| [YOLO26m-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-pose.pt) | 640                   | 68.8                  | 89.9               | 218.0 ± 1.5                    | 5.0 ± 0.1                           | 21.5               | 73.1              |
-| [YOLO26l-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-pose.pt) | 640                   | 70.4                  | 90.8               | 275.4 ± 2.4                    | 6.5 ± 0.1                           | 25.9               | 91.3              |
-| [YOLO26x-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-pose.pt) | 640                   | 71.7                  | 91.6               | 565.4 ± 3.0                    | 12.2 ± 0.2                          | 57.6               | 201.7             |
+| [YOLO26n-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-pose.pt) | 640                   | 57.2                  | 83.3               | 40.3 ± 0.5                     | 1.8 ± 0.0                           | 2.9                | 7.5               |
+| [YOLO26s-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-pose.pt) | 640                   | 63.0                  | 86.6               | 85.3 ± 0.9                     | 2.7 ± 0.0                           | 10.4               | 23.9              |
+| [YOLO26m-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-pose.pt) | 640                   | 68.8                  | 89.6               | 218.0 ± 1.5                    | 5.0 ± 0.1                           | 21.5               | 73.1              |
+| [YOLO26l-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-pose.pt) | 640                   | 70.4                  | 90.5               | 275.4 ± 2.4                    | 6.5 ± 0.1                           | 25.9               | 91.3              |
+| [YOLO26x-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-pose.pt) | 640                   | 71.6                  | 91.6               | 565.4 ± 3.0                    | 12.2 ± 0.2                          | 57.6               | 201.7             |
 
 - **mAP<sup>val</sup>** values are for single-model single-scale on the [COCO Keypoints val2017](https://docs.ultralytics.com/datasets/pose/coco/) dataset. See [YOLO Performance Metrics](https://docs.ultralytics.com/guides/yolo-performance-metrics/) for details. <br>Reproduce with `yolo val pose data=coco-pose.yaml device=0`
 - **Speed** metrics are averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce with `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@@ -289,10 +289,10 @@ Check the [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples
 | Model                                                                                        | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
 | [YOLO26n-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-obb.pt) | 1024                  | 78.9               | 97.7 ± 0.9                     | 2.8 ± 0.0                           | 2.5                | 14.0              |
-| [YOLO26s-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-obb.pt) | 1024                  | 79.8               | 218.0 ± 1.4                    | 4.9 ± 0.1                           | 9.8                | 55.1              |
+| [YOLO26s-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-obb.pt) | 1024                  | 80.9               | 218.0 ± 1.4                    | 4.9 ± 0.1                           | 9.8                | 55.1              |
 | [YOLO26m-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-obb.pt) | 1024                  | 81.0               | 579.2 ± 3.8                    | 10.2 ± 0.3                          | 21.2               | 183.3             |
-| [YOLO26l-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-obb.pt) | 1024                  | 81.4               | 735.6 ± 3.1                    | 13.0 ± 0.2                          | 25.6               | 230.0             |
-| [YOLO26x-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-obb.pt) | 1024                  | 82.1               | 1485.7 ± 11.5                  | 30.5 ± 0.9                          | 57.6               | 516.5             |
+| [YOLO26l-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-obb.pt) | 1024                  | 81.6               | 735.6 ± 3.1                    | 13.0 ± 0.2                          | 25.6               | 230.0             |
+| [YOLO26x-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-obb.pt) | 1024                  | 81.7               | 1485.7 ± 11.5                  | 30.5 ± 0.9                          | 57.6               | 516.5             |
 
 - **mAP<sup>test</sup>** values are for single-model multiscale performance on the [DOTAv1 test set](https://captain-whu.github.io/DOTA/dataset.html). <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to the [DOTA evaluation server](https://captain-whu.github.io/DOTA/evaluation.html).
 - **Speed** metrics are averaged over [DOTAv1 val images](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10) using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/README.md

@@ -148,11 +148,11 @@ Refer to the [Segmentation Docs](https://docs.ultralytics.com/tasks/segment/) fo
 
 | Model                                                                                        | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO26n-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-seg.pt) | 640                   | 39.6                 | 33.9                  | 53.3 ± 0.5                     | 2.1 ± 0.0                           | 2.8                | 9.1               |
-| [YOLO26s-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-seg.pt) | 640                   | 47.3                 | 40.0                  | 118.4 ± 0.9                    | 3.3 ± 0.0                           | 10.7               | 34.2              |
-| [YOLO26m-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-seg.pt) | 640                   | 52.5                 | 44.1                  | 328.2 ± 2.4                    | 6.7 ± 0.1                           | 24.8               | 121.5             |
-| [YOLO26l-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-seg.pt) | 640                   | 54.4                 | 45.5                  | 387.0 ± 3.7                    | 8.0 ± 0.1                           | 29.2               | 139.8             |
-| [YOLO26x-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-seg.pt) | 640                   | 56.5                 | 47.0                  | 787.0 ± 6.8                    | 16.4 ± 0.1                          | 65.5               | 313.5             |
+| [YOLO26n-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-seg.pt) | 640                   | 39.6                 | 33.9                  | 53.3 ± 0.5                     | 2.1 ± 0.0                           | 2.7                | 9.1               |
+| [YOLO26s-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-seg.pt) | 640                   | 47.3                 | 40.0                  | 118.4 ± 0.9                    | 3.3 ± 0.0                           | 10.4               | 34.2              |
+| [YOLO26m-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-seg.pt) | 640                   | 52.5                 | 44.1                  | 328.2 ± 2.4                    | 6.7 ± 0.1                           | 23.6               | 121.5             |
+| [YOLO26l-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-seg.pt) | 640                   | 54.4                 | 45.5                  | 387.0 ± 3.7                    | 8.0 ± 0.1                           | 28.0               | 139.8             |
+| [YOLO26x-seg](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-seg.pt) | 640                   | 56.5                 | 47.0                  | 787.0 ± 6.8                    | 16.4 ± 0.1                          | 62.8               | 313.5             |
 
 - **mAP<sup>val</sup>** values are for single-model single-scale on the [COCO val2017](https://cocodataset.org/) dataset. See [YOLO Performance Metrics](https://docs.ultralytics.com/guides/yolo-performance-metrics/) for details. <br>Reproduce with `yolo val segment data=coco.yaml device=0`
 - **Speed** metrics are averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce with `yolo val segment data=coco.yaml batch=1 device=0|cpu`
@@ -182,11 +182,11 @@ See the [Pose Estimation Docs](https://docs.ultralytics.com/tasks/pose/) for usa
 
 | Model                                                                                          | size<br><sup>(pixels) | mAP<sup>pose<br>50-95 | mAP<sup>pose<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | ---------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO26n-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-pose.pt) | 640                   | 56.9                  | 83.0               | 40.3 ± 0.5                     | 1.8 ± 0.0                           | 2.9                | 7.5               |
-| [YOLO26s-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-pose.pt) | 640                   | 63.1                  | 86.8               | 85.3 ± 0.9                     | 2.7 ± 0.0                           | 10.4               | 23.9              |
-| [YOLO26m-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-pose.pt) | 640                   | 68.8                  | 89.9               | 218.0 ± 1.5                    | 5.0 ± 0.1                           | 21.5               | 73.1              |
-| [YOLO26l-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-pose.pt) | 640                   | 70.4                  | 90.8               | 275.4 ± 2.4                    | 6.5 ± 0.1                           | 25.9               | 91.3              |
-| [YOLO26x-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-pose.pt) | 640                   | 71.7                  | 91.6               | 565.4 ± 3.0                    | 12.2 ± 0.2                          | 57.6               | 201.7             |
+| [YOLO26n-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-pose.pt) | 640                   | 57.2                  | 83.3               | 40.3 ± 0.5                     | 1.8 ± 0.0                           | 2.9                | 7.5               |
+| [YOLO26s-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-pose.pt) | 640                   | 63.0                  | 86.6               | 85.3 ± 0.9                     | 2.7 ± 0.0                           | 10.4               | 23.9              |
+| [YOLO26m-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-pose.pt) | 640                   | 68.8                  | 89.6               | 218.0 ± 1.5                    | 5.0 ± 0.1                           | 21.5               | 73.1              |
+| [YOLO26l-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-pose.pt) | 640                   | 70.4                  | 90.5               | 275.4 ± 2.4                    | 6.5 ± 0.1                           | 25.9               | 91.3              |
+| [YOLO26x-pose](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-pose.pt) | 640                   | 71.6                  | 91.6               | 565.4 ± 3.0                    | 12.2 ± 0.2                          | 57.6               | 201.7             |
 
 - **mAP<sup>val</sup>** values are for single-model single-scale on the [COCO Keypoints val2017](https://docs.ultralytics.com/datasets/pose/coco/) dataset. See [YOLO Performance Metrics](https://docs.ultralytics.com/guides/yolo-performance-metrics/) for details. <br>Reproduce with `yolo val pose data=coco-pose.yaml device=0`
 - **Speed** metrics are averaged over COCO val images using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce with `yolo val pose data=coco-pose.yaml batch=1 device=0|cpu`
@@ -200,10 +200,10 @@ Check the [OBB Docs](https://docs.ultralytics.com/tasks/obb/) for usage examples
 | Model                                                                                        | size<br><sup>(pixels) | mAP<sup>test<br>50 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) |
 | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
 | [YOLO26n-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n-obb.pt) | 1024                  | 78.9               | 97.7 ± 0.9                     | 2.8 ± 0.0                           | 2.5                | 14.0              |
-| [YOLO26s-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-obb.pt) | 1024                  | 79.8               | 218.0 ± 1.4                    | 4.9 ± 0.1                           | 9.8                | 55.1              |
+| [YOLO26s-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s-obb.pt) | 1024                  | 80.9               | 218.0 ± 1.4                    | 4.9 ± 0.1                           | 9.8                | 55.1              |
 | [YOLO26m-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26m-obb.pt) | 1024                  | 81.0               | 579.2 ± 3.8                    | 10.2 ± 0.3                          | 21.2               | 183.3             |
-| [YOLO26l-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-obb.pt) | 1024                  | 81.4               | 735.6 ± 3.1                    | 13.0 ± 0.2                          | 25.6               | 230.0             |
-| [YOLO26x-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-obb.pt) | 1024                  | 82.1               | 1485.7 ± 11.5                  | 30.5 ± 0.9                          | 57.6               | 516.5             |
+| [YOLO26l-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26l-obb.pt) | 1024                  | 81.6               | 735.6 ± 3.1                    | 13.0 ± 0.2                          | 25.6               | 230.0             |
+| [YOLO26x-obb](https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26x-obb.pt) | 1024                  | 81.7               | 1485.7 ± 11.5                  | 30.5 ± 0.9                          | 57.6               | 516.5             |
 
 - **mAP<sup>test</sup>** values are for single-model multiscale performance on the [DOTAv1 test set](https://captain-whu.github.io/DOTA/dataset.html). <br>Reproduce by `yolo val obb data=DOTAv1.yaml device=0 split=test` and submit merged results to the [DOTA evaluation server](https://captain-whu.github.io/DOTA/evaluation.html).
 - **Speed** metrics are averaged over [DOTAv1 val images](https://docs.ultralytics.com/datasets/obb/dota-v2/#dota-v10) using an [Amazon EC2 P4d](https://aws.amazon.com/ec2/instance-types/p4/) instance. CPU speeds measured with [ONNX](https://onnx.ai/) export. GPU speeds measured with [TensorRT](https://developer.nvidia.com/tensorrt) export. <br>Reproduce by `yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu`

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/tests/test_engine.py

@@ -5,7 +5,7 @@ from unittest import mock
 
 import torch
 
-from tests import MODEL
+from tests import MODEL, SOURCE
 from ultralytics import YOLO
 from ultralytics.cfg import get_cfg
 from ultralytics.engine.exporter import Exporter
@@ -24,7 +24,7 @@ def test_export():
     exporter.add_callback("on_export_start", test_func)
     assert test_func in exporter.callbacks["on_export_start"], "callback test failed"
     f = exporter(model=YOLO("yolo26n.yaml").model)
-    YOLO(f)(ASSETS)  # exported model inference
+    YOLO(f)(SOURCE)  # exported model inference
 
 
 def test_detect():

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/tests/test_exports.py

@@ -144,7 +144,9 @@ def test_export_coreml_matrix(task, dynamic, int8, half, nms, batch):
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10, reason="TFLite export requires Python>=3.10")
+@pytest.mark.skipif(
+    not checks.IS_PYTHON_MINIMUM_3_10 or not TORCH_1_13, reason="TFLite export requires Python>=3.10 and torch>=1.13"
+)
 @pytest.mark.skipif(
     not LINUX or IS_RASPBERRYPI,
     reason="Test disabled as TF suffers from install conflicts on Windows, macOS and Raspberry Pi",
@@ -238,7 +240,6 @@ def test_export_mnn_matrix(task, int8, half, batch):
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(ARM64, reason="NCNN not supported on ARM64")  # https://github.com/Tencent/ncnn/issues/6509
 @pytest.mark.skipif(not TORCH_2_0, reason="NCNN inference causes segfault on PyTorch<2.0")
 def test_export_ncnn():
     """Test YOLO export to NCNN format."""
@@ -247,7 +248,6 @@ def test_export_ncnn():
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(ARM64, reason="NCNN not supported on ARM64")  # https://github.com/Tencent/ncnn/issues/6509
 @pytest.mark.skipif(not TORCH_2_0, reason="NCNN inference causes segfault on PyTorch<2.0")
 @pytest.mark.parametrize("task, half, batch", list(product(TASKS, [True, False], [1])))
 def test_export_ncnn_matrix(task, half, batch):

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.4.0"
+__version__ = "8.4.2"
 
 import importlib
 import os

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/__init__.py

@@ -305,8 +305,6 @@ def get_cfg(
     # Merge overrides
     if overrides:
         overrides = cfg2dict(overrides)
-        if "save_dir" not in cfg:
-            overrides.pop("save_dir", None)  # special override keys to ignore
         check_dict_alignment(cfg, overrides)
         cfg = {**cfg, **overrides}  # merge cfg and overrides dicts (prefer overrides)
 
@@ -494,7 +492,7 @@ def check_dict_alignment(
     base_keys, custom_keys = (frozenset(x.keys()) for x in (base, custom))
     # Allow 'augmentations' as a valid custom parameter for custom Albumentations transforms
     if allowed_custom_keys is None:
-        allowed_custom_keys = {"augmentations"}
+        allowed_custom_keys = {"augmentations", "save_dir"}
     if mismatched := [k for k in custom_keys if k not in base_keys and k not in allowed_custom_keys]:
         from difflib import get_close_matches
 

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-cls.yaml

@@ -1,12 +1,12 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLO26-cls image classification model
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/classify
 
 # Parameters
 nc: 1000 # number of classes
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n-cls.yaml' will call yolo26-cls.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 86 layers, 2,812,104 parameters, 2,812,104 gradients, 0.5 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 86 layers, 6,724,008 parameters, 6,724,008 gradients, 1.6 GFLOPs

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-obb.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLO26-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/obb
 
@@ -8,7 +8,7 @@
 nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n-obb.yaml' will call yolo26-obb.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 291 layers, 2,715,614 parameters, 2,715,614 gradients, 16.9 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 291 layers, 10,582,142 parameters, 10,582,142 gradients, 63.5 GFLOPs

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-p2.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLO26 object detection model with P2/4 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/detect
 
@@ -8,13 +8,13 @@
 nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n-p2.yaml' will call yolo26-p2.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.50, 0.25, 1024] # summary: 181 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
-  s: [0.50, 0.50, 1024] # summary: 181 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
-  m: [0.50, 1.00, 512] # summary: 231 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
-  l: [1.00, 1.00, 512] # summary: 357 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
-  x: [1.00, 1.50, 512] # summary: 357 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
+  n: [0.50, 0.25, 1024] # summary: 329 layers, 2,662,400 parameters, 2,662,400 gradients, 9.5 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 329 layers, 9,765,856 parameters, 9,765,856 gradients, 27.8 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 349 layers, 21,144,288 parameters, 21,144,288 gradients, 91.4 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 489 layers, 25,815,520 parameters, 25,815,520 gradients, 115.3 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 489 layers, 57,935,232 parameters, 57,935,232 gradients, 256.9 GFLOPs
 
 # YOLO26n backbone
 backbone:
@@ -42,12 +42,12 @@ head:
   - [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
 
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
-  - [[-1, 2], 1, Concat, [1]] # cat backbone P3
-  - [-1, 2, C3k2, [128, True]] # 19 (P3/8-small)
+  - [[-1, 2], 1, Concat, [1]] # cat backbone P2
+  - [-1, 2, C3k2, [128, True]] # 19 (P2/4-xsmall)
 
   - [-1, 1, Conv, [128, 3, 2]]
   - [[-1, 16], 1, Concat, [1]] # cat head P3
-  - [-1, 2, C3k2, [256, True]] # 22 (P4/16-medium)
+  - [-1, 2, C3k2, [256, True]] # 22 (P3/8-small)
 
   - [-1, 1, Conv, [256, 3, 2]]
   - [[-1, 13], 1, Concat, [1]] # cat head P4
@@ -57,4 +57,4 @@ head:
   - [[-1, 10], 1, Concat, [1]] # cat head P5
   - [-1, 1, C3k2, [1024, True, 0.5, True]] # 28 (P5/32-large)
 
-  - [[19, 22, 25, 28], 1, Detect, [nc]] # Detect(P3, P4, P5)
+  - [[19, 22, 25, 28], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-p6.yaml

@@ -6,13 +6,15 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+end2end: True # whether to use end-to-end mode
+reg_max: 1 # DFL bins
+scales: # model compound scaling constants, i.e. 'model=yolo26n-p6.yaml' will call yolo26-p6.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
-  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
-  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
-  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
+  n: [0.50, 0.25, 1024] # summary: 349 layers, 4,063,872 parameters, 4,063,872 gradients, 6.0 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 349 layers, 15,876,448 parameters, 15,876,448 gradients, 22.3 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 369 layers, 32,400,096 parameters, 32,400,096 gradients, 77.3 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 523 layers, 39,365,600 parameters, 39,365,600 gradients, 97.0 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 523 layers, 88,330,368 parameters, 88,330,368 gradients, 216.6 GFLOPs
 
 # YOLO26n backbone
 backbone:

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-pose.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLO26-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/pose
 
@@ -9,7 +9,7 @@ nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
 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=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n-pose.yaml' will call yolo26-pose.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 363 layers, 3,747,554 parameters, 3,747,554 gradients, 10.7 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 363 layers, 11,870,498 parameters, 11,870,498 gradients, 29.6 GFLOPs

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26-seg.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLO26-seg instance segmentation model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/segment
 
@@ -8,7 +8,7 @@
 nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n-seg.yaml' will call yolo26-seg.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 309 layers, 3,126,280 parameters, 3,126,280 gradients, 10.5 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 309 layers, 11,505,800 parameters, 11,505,800 gradients, 37.4 GFLOPs

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yolo26.yaml

@@ -8,7 +8,7 @@
 nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
   s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yoloe-26-seg.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLOE-26 open-vocabulary instance segmentation model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/segment
 
@@ -9,15 +9,15 @@ nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
 text_model: mobileclip2:b
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yoloe-26n-seg.yaml' will call yoloe-26-seg.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.50, 0.25, 1024] # summary: 181 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
-  s: [0.50, 0.50, 1024] # summary: 181 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
-  m: [0.50, 1.00, 512] # summary: 231 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
-  l: [1.00, 1.00, 512] # summary: 357 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
-  x: [1.00, 1.50, 512] # summary: 357 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
+  n: [0.50, 0.25, 1024] # summary: 347 layers, 5,615,540 parameters, 5,615,540 gradients, 11.7 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 347 layers, 15,272,852 parameters, 15,272,852 gradients, 39.3 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 367 layers, 34,922,132 parameters, 34,922,132 gradients, 136.3 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 479 layers, 39,325,588 parameters, 39,325,588 gradients, 154.7 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 479 layers, 85,397,684 parameters, 85,397,684 gradients, 343.3 GFLOPs
 
-# YOLO26n backbone
+# YOLOE26n backbone
 backbone:
   # [from, repeats, module, args]
   - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
@@ -32,7 +32,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5, 3, True]] # 9
   - [-1, 2, C2PSA, [1024]] # 10
 
-# YOLO26n head
+# YOLOE26n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4
@@ -50,4 +50,4 @@ head:
   - [[-1, 10], 1, Concat, [1]] # cat head P5
   - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
 
-  - [[16, 19, 22], 1, YOLOESegment26, [nc, 32, 256, 512, True]] # Detect(P3, P4, P5)
+  - [[16, 19, 22], 1, YOLOESegment26, [nc, 32, 256, 512, True]] # YOLOESegment26(P3, P4, P5)

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/cfg/models/26/yoloe-26.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
+# Ultralytics YOLOE-26 open-vocabulary object detection model with P3/8 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolo26
 # Task docs: https://docs.ultralytics.com/tasks/detect
 
@@ -9,15 +9,15 @@ nc: 80 # number of classes
 end2end: True # whether to use end-to-end mode
 reg_max: 1 # DFL bins
 text_model: mobileclip2:b
-scales: # model compound scaling constants, i.e. 'model=YOLO26n.yaml' will call YOLO26.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yoloe-26n.yaml' will call yoloe-26.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.50, 0.25, 1024] # summary: 181 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
-  s: [0.50, 0.50, 1024] # summary: 181 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
-  m: [0.50, 1.00, 512] # summary: 231 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
-  l: [1.00, 1.00, 512] # summary: 357 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
-  x: [1.00, 1.50, 512] # summary: 357 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
+  n: [0.50, 0.25, 1024] # summary: 298 layers, 5,061,540 parameters, 5,061,540 gradients, 7.3 GFLOPs
+  s: [0.50, 0.50, 1024] # summary: 298 layers, 13,776,836 parameters, 13,776,836 gradients, 24.8 GFLOPs
+  m: [0.50, 1.00, 512] # summary: 318 layers, 29,706,308 parameters, 29,706,308 gradients, 79.2 GFLOPs
+  l: [1.00, 1.00, 512] # summary: 430 layers, 34,109,764 parameters, 34,109,764 gradients, 97.6 GFLOPs
+  x: [1.00, 1.50, 512] # summary: 430 layers, 73,697,252 parameters, 73,697,252 gradients, 215.2 GFLOPs
 
-# YOLO26n backbone
+# YOLOE26n backbone
 backbone:
   # [from, repeats, module, args]
   - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
@@ -32,7 +32,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5, 3, True]] # 9
   - [-1, 2, C2PSA, [1024]] # 10
 
-# YOLO26n head
+# YOLOE26n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4
@@ -50,4 +50,4 @@ head:
   - [[-1, 10], 1, Concat, [1]] # cat head P5
   - [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
 
-  - [[16, 19, 22], 1, YOLOEDetect, [nc, 512, True]] # Detect(P3, P4, P5)
+  - [[16, 19, 22], 1, YOLOEDetect, [nc, 512, True]] # YOLOEDetect(P3, P4, P5)

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/data/converter.py

@@ -749,12 +749,13 @@ def convert_to_multispectral(path: str | Path, n_channels: int = 10, replace: bo
 async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Path | None = None) -> Path:
     """Convert NDJSON dataset format to Ultralytics YOLO11 dataset structure.
 
-    This function converts datasets stored in NDJSON (Newline Delimited JSON) format to the standard YOLO format with
-    separate directories for images and labels. It supports parallel processing for efficient conversion of large
-    datasets and can download images from URLs if they don't exist locally.
+    This function converts datasets stored in NDJSON (Newline Delimited JSON) format to the standard YOLO format. For
+    detection/segmentation/pose/obb tasks, it creates separate directories for images and labels. For classification
+    tasks, it creates the ImageNet-style {split}/{class_name}/ folder structure. It supports parallel processing for
+    efficient conversion of large datasets and can download images from URLs.
 
     The NDJSON format consists of:
-    - First line: Dataset metadata with class names and configuration
+    - First line: Dataset metadata with class names, task type, and configuration
     - Subsequent lines: Individual image records with annotations and optional URLs
 
     Args:
@@ -763,7 +764,7 @@ async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Pat
             None, uses the parent directory of the NDJSON file. Defaults to None.
 
     Returns:
-        (Path): Path to the generated data.yaml file that can be used for YOLO training.
+        (Path): Path to the generated data.yaml file (detection) or dataset directory (classification).
 
     Examples:
         Convert a local NDJSON file:
@@ -790,36 +791,51 @@ async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Pat
     dataset_dir = output_path / ndjson_path.stem
     splits = {record["split"] for record in image_records}
 
-    # Create directories and prepare YAML structure
-    dataset_dir.mkdir(parents=True, exist_ok=True)
-    data_yaml = dict(dataset_record)
-    data_yaml["names"] = {int(k): v for k, v in dataset_record.get("class_names", {}).items()}
-    data_yaml.pop("class_names")
+    # Check if this is a classification dataset
+    is_classification = dataset_record.get("task") == "classify"
+    class_names = {int(k): v for k, v in dataset_record.get("class_names", {}).items()}
 
-    for split in sorted(splits):
-        (dataset_dir / "images" / split).mkdir(parents=True, exist_ok=True)
-        (dataset_dir / "labels" / split).mkdir(parents=True, exist_ok=True)
-        data_yaml[split] = f"images/{split}"
+    # Create base directories
+    dataset_dir.mkdir(parents=True, exist_ok=True)
+    data_yaml = None
+
+    if not is_classification:
+        # Detection/segmentation/pose/obb: prepare YAML and create base structure
+        data_yaml = dict(dataset_record)
+        data_yaml["names"] = class_names
+        data_yaml.pop("class_names", None)
+        data_yaml.pop("type", None)  # Remove NDJSON-specific fields
+        for split in sorted(splits):
+            (dataset_dir / "images" / split).mkdir(parents=True, exist_ok=True)
+            (dataset_dir / "labels" / split).mkdir(parents=True, exist_ok=True)
+            data_yaml[split] = f"images/{split}"
 
     async def process_record(session, semaphore, record):
         """Process single image record with async session."""
         async with semaphore:
             split, original_name = record["split"], record["file"]
-            label_path = dataset_dir / "labels" / split / f"{Path(original_name).stem}.txt"
-            image_path = dataset_dir / "images" / split / original_name
-
             annotations = record.get("annotations", {})
-            lines_to_write = []
-            for key in annotations.keys():
-                lines_to_write = [" ".join(map(str, item)) for item in annotations[key]]
-                break
-            if "classification" in annotations:
-                lines_to_write = [str(cls) for cls in annotations["classification"]]
-
-            label_path.write_text("\n".join(lines_to_write) + "\n" if lines_to_write else "")
 
+            if is_classification:
+                # Classification: place image in {split}/{class_name}/ folder
+                class_ids = annotations.get("classification", [])
+                class_id = class_ids[0] if class_ids else 0
+                class_name = class_names.get(class_id, str(class_id))
+                image_path = dataset_dir / split / class_name / original_name
+            else:
+                # Detection: write label file and place image in images/{split}/
+                image_path = dataset_dir / "images" / split / original_name
+                label_path = dataset_dir / "labels" / split / f"{Path(original_name).stem}.txt"
+                lines_to_write = []
+                for key in annotations.keys():
+                    lines_to_write = [" ".join(map(str, item)) for item in annotations[key]]
+                    break
+                label_path.write_text("\n".join(lines_to_write) + "\n" if lines_to_write else "")
+
+            # Download image if URL provided and file doesn't exist
             if http_url := record.get("url"):
                 if not image_path.exists():
+                    image_path.parent.mkdir(parents=True, exist_ok=True)  # Ensure parent dir exists
                     try:
                         async with session.get(http_url, timeout=aiohttp.ClientTimeout(total=30)) as response:
                             response.raise_for_status()
@@ -848,8 +864,11 @@ async def convert_ndjson_to_yolo(ndjson_path: str | Path, output_path: str | Pat
         await asyncio.gather(*[tracked_process(record) for record in image_records])
         pbar.close()
 
-    # Write data.yaml
-    yaml_path = dataset_dir / "data.yaml"
-    YAML.save(yaml_path, data_yaml)
-
-    return yaml_path
+    if is_classification:
+        # Classification: return dataset directory (check_cls_dataset expects a directory path)
+        return dataset_dir
+    else:
+        # Detection: write data.yaml and return its path
+        yaml_path = dataset_dir / "data.yaml"
+        YAML.save(yaml_path, data_yaml)
+        return yaml_path

{ultralytics_opencv_headless-8.4.0 → ultralytics_opencv_headless-8.4.2}/ultralytics/engine/exporter.py

@@ -463,6 +463,9 @@ class Exporter:
             )
         if tfjs and (ARM64 and LINUX):
             raise SystemError("TF.js exports are not currently supported on ARM64 Linux")
+        if ncnn and hasattr(model.model[-1], "one2one_cv2"):
+            del model.model[-1].one2one_cv2  # Disable end2end branch for NCNN export as it does not support topk
+            LOGGER.warning("NCNN export does not support end2end models, disabling end2end branch.")
         # Recommend OpenVINO if export and Intel CPU
         if SETTINGS.get("openvino_msg"):
             if is_intel():
@@ -791,7 +794,6 @@ class Exporter:
                         f".*{head_module_name}/.*/Sub*",
                         f".*{head_module_name}/.*/Mul*",
                         f".*{head_module_name}/.*/Div*",
-                        f".*{head_module_name}\\.dfl.*",
                     ],
                     types=["Sigmoid"],
                 )
@@ -864,10 +866,6 @@ class Exporter:
     @try_export
     def export_ncnn(self, prefix=colorstr("NCNN:")):
         """Export YOLO model to NCNN format using PNNX https://github.com/pnnx/pnnx."""
-        if ARM64:
-            raise NotImplementedError(
-                "NCNN export is not supported on ARM64"
-            )  # https://github.com/Tencent/ncnn/issues/6509
         check_requirements("ncnn", cmds="--no-deps")  # no deps to avoid installing opencv-python
         check_requirements("pnnx")
         import ncnn