ultralytics 8.3.203__tar.gz → 8.3.204__tar.gz

{ultralytics-8.3.203 → ultralytics-8.3.204}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.203
+Version: 8.3.204
 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>
@@ -239,11 +239,11 @@ 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) |
 | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-seg.pt) | 640                   | 38.9                 | 32.0                  | 65.9 ± 1.1                     | 1.8 ± 0.0                           | 2.9                | 10.4              |
-| [YOLO11s-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-seg.pt) | 640                   | 46.6                 | 37.8                  | 117.6 ± 4.9                    | 2.9 ± 0.0                           | 10.1               | 35.5              |
-| [YOLO11m-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-seg.pt) | 640                   | 51.5                 | 41.5                  | 281.6 ± 1.2                    | 6.3 ± 0.1                           | 22.4               | 123.3             |
-| [YOLO11l-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-seg.pt) | 640                   | 53.4                 | 42.9                  | 344.2 ± 3.2                    | 7.8 ± 0.2                           | 27.6               | 142.2             |
-| [YOLO11x-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-seg.pt) | 640                   | 54.7                 | 43.8                  | 664.5 ± 3.2                    | 15.8 ± 0.7                          | 62.1               | 319.0             |
+| [YOLO11n-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-seg.pt) | 640                   | 38.9                 | 32.0                  | 65.9 ± 1.1                     | 1.8 ± 0.0                           | 2.9                | 9.7               |
+| [YOLO11s-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-seg.pt) | 640                   | 46.6                 | 37.8                  | 117.6 ± 4.9                    | 2.9 ± 0.0                           | 10.1               | 33.0              |
+| [YOLO11m-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-seg.pt) | 640                   | 51.5                 | 41.5                  | 281.6 ± 1.2                    | 6.3 ± 0.1                           | 22.4               | 113.2             |
+| [YOLO11l-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-seg.pt) | 640                   | 53.4                 | 42.9                  | 344.2 ± 3.2                    | 7.8 ± 0.2                           | 27.6               | 132.2             |
+| [YOLO11x-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-seg.pt) | 640                   | 54.7                 | 43.8                  | 664.5 ± 3.2                    | 15.8 ± 0.7                          | 62.1               | 296.4             |
 
 - **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`
@@ -256,11 +256,11 @@ Consult the [Classification Docs](https://docs.ultralytics.com/tasks/classify/)
 
 | Model                                                                                        | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 224 |
 | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
-| [YOLO11n-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-cls.pt) | 224                   | 70.0             | 89.4             | 5.0 ± 0.3                      | 1.1 ± 0.0                           | 1.6                | 0.5                      |
-| [YOLO11s-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-cls.pt) | 224                   | 75.4             | 92.7             | 7.9 ± 0.2                      | 1.3 ± 0.0                           | 5.5                | 1.6                      |
-| [YOLO11m-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-cls.pt) | 224                   | 77.3             | 93.9             | 17.2 ± 0.4                     | 2.0 ± 0.0                           | 10.4               | 5.0                      |
-| [YOLO11l-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-cls.pt) | 224                   | 78.3             | 94.3             | 23.2 ± 0.3                     | 2.8 ± 0.0                           | 12.9               | 6.2                      |
-| [YOLO11x-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-cls.pt) | 224                   | 79.5             | 94.9             | 41.4 ± 0.9                     | 3.8 ± 0.0                           | 28.4               | 13.7                     |
+| [YOLO11n-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-cls.pt) | 224                   | 70.0             | 89.4             | 5.0 ± 0.3                      | 1.1 ± 0.0                           | 2.8                | 0.5                      |
+| [YOLO11s-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-cls.pt) | 224                   | 75.4             | 92.7             | 7.9 ± 0.2                      | 1.3 ± 0.0                           | 6.7                | 1.6                      |
+| [YOLO11m-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-cls.pt) | 224                   | 77.3             | 93.9             | 17.2 ± 0.4                     | 2.0 ± 0.0                           | 11.6               | 4.9                      |
+| [YOLO11l-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-cls.pt) | 224                   | 78.3             | 94.3             | 23.2 ± 0.3                     | 2.8 ± 0.0                           | 14.1               | 6.2                      |
+| [YOLO11x-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-cls.pt) | 224                   | 79.5             | 94.9             | 41.4 ± 0.9                     | 3.8 ± 0.0                           | 29.6               | 13.6                     |
 
 - **acc** values represent model accuracy on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce with `yolo val classify data=path/to/ImageNet device=0`
 - **Speed** metrics are averaged over ImageNet 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 classify data=path/to/ImageNet batch=1 device=0|cpu`
@@ -273,11 +273,11 @@ 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) |
 | ---------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-pose.pt) | 640                   | 50.0                  | 81.0               | 52.4 ± 0.5                     | 1.7 ± 0.0                           | 2.9                | 7.6               |
-| [YOLO11s-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-pose.pt) | 640                   | 58.9                  | 86.3               | 90.5 ± 0.6                     | 2.6 ± 0.0                           | 9.9                | 23.2              |
-| [YOLO11m-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-pose.pt) | 640                   | 64.9                  | 89.4               | 187.3 ± 0.8                    | 4.9 ± 0.1                           | 20.9               | 71.7              |
-| [YOLO11l-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-pose.pt) | 640                   | 66.1                  | 89.9               | 247.7 ± 1.1                    | 6.4 ± 0.1                           | 26.2               | 90.7              |
-| [YOLO11x-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-pose.pt) | 640                   | 69.5                  | 91.1               | 488.0 ± 13.9                   | 12.1 ± 0.2                          | 58.8               | 203.3             |
+| [YOLO11n-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-pose.pt) | 640                   | 50.0                  | 81.0               | 52.4 ± 0.5                     | 1.7 ± 0.0                           | 2.9                | 7.4               |
+| [YOLO11s-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-pose.pt) | 640                   | 58.9                  | 86.3               | 90.5 ± 0.6                     | 2.6 ± 0.0                           | 9.9                | 23.1              |
+| [YOLO11m-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-pose.pt) | 640                   | 64.9                  | 89.4               | 187.3 ± 0.8                    | 4.9 ± 0.1                           | 20.9               | 71.4              |
+| [YOLO11l-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-pose.pt) | 640                   | 66.1                  | 89.9               | 247.7 ± 1.1                    | 6.4 ± 0.1                           | 26.1               | 90.3              |
+| [YOLO11x-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-pose.pt) | 640                   | 69.5                  | 91.1               | 488.0 ± 13.9                   | 12.1 ± 0.2                          | 58.8               | 202.8             |
 
 - **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`
@@ -290,11 +290,11 @@ 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) |
 | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-obb.pt) | 1024                  | 78.4               | 117.6 ± 0.8                    | 4.4 ± 0.0                           | 2.7                | 17.2              |
-| [YOLO11s-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-obb.pt) | 1024                  | 79.5               | 219.4 ± 4.0                    | 5.1 ± 0.0                           | 9.7                | 57.5              |
-| [YOLO11m-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-obb.pt) | 1024                  | 80.9               | 562.8 ± 2.9                    | 10.1 ± 0.4                          | 20.9               | 183.5             |
-| [YOLO11l-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-obb.pt) | 1024                  | 81.0               | 712.5 ± 5.0                    | 13.5 ± 0.6                          | 26.2               | 232.0             |
-| [YOLO11x-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-obb.pt) | 1024                  | 81.3               | 1408.6 ± 7.7                   | 28.6 ± 1.0                          | 58.8               | 520.2             |
+| [YOLO11n-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-obb.pt) | 1024                  | 78.4               | 117.6 ± 0.8                    | 4.4 ± 0.0                           | 2.7                | 16.8              |
+| [YOLO11s-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-obb.pt) | 1024                  | 79.5               | 219.4 ± 4.0                    | 5.1 ± 0.0                           | 9.7                | 57.1              |
+| [YOLO11m-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-obb.pt) | 1024                  | 80.9               | 562.8 ± 2.9                    | 10.1 ± 0.4                          | 20.9               | 182.8             |
+| [YOLO11l-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-obb.pt) | 1024                  | 81.0               | 712.5 ± 5.0                    | 13.5 ± 0.6                          | 26.1               | 231.2             |
+| [YOLO11x-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-obb.pt) | 1024                  | 81.3               | 1408.6 ± 7.7                   | 28.6 ± 1.0                          | 58.8               | 519.1             |
 
 - **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-8.3.203 → ultralytics-8.3.204}/README.md

@@ -149,11 +149,11 @@ 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) |
 | -------------------------------------------------------------------------------------------- | --------------------- | -------------------- | --------------------- | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-seg.pt) | 640                   | 38.9                 | 32.0                  | 65.9 ± 1.1                     | 1.8 ± 0.0                           | 2.9                | 10.4              |
-| [YOLO11s-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-seg.pt) | 640                   | 46.6                 | 37.8                  | 117.6 ± 4.9                    | 2.9 ± 0.0                           | 10.1               | 35.5              |
-| [YOLO11m-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-seg.pt) | 640                   | 51.5                 | 41.5                  | 281.6 ± 1.2                    | 6.3 ± 0.1                           | 22.4               | 123.3             |
-| [YOLO11l-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-seg.pt) | 640                   | 53.4                 | 42.9                  | 344.2 ± 3.2                    | 7.8 ± 0.2                           | 27.6               | 142.2             |
-| [YOLO11x-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-seg.pt) | 640                   | 54.7                 | 43.8                  | 664.5 ± 3.2                    | 15.8 ± 0.7                          | 62.1               | 319.0             |
+| [YOLO11n-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-seg.pt) | 640                   | 38.9                 | 32.0                  | 65.9 ± 1.1                     | 1.8 ± 0.0                           | 2.9                | 9.7               |
+| [YOLO11s-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-seg.pt) | 640                   | 46.6                 | 37.8                  | 117.6 ± 4.9                    | 2.9 ± 0.0                           | 10.1               | 33.0              |
+| [YOLO11m-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-seg.pt) | 640                   | 51.5                 | 41.5                  | 281.6 ± 1.2                    | 6.3 ± 0.1                           | 22.4               | 113.2             |
+| [YOLO11l-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-seg.pt) | 640                   | 53.4                 | 42.9                  | 344.2 ± 3.2                    | 7.8 ± 0.2                           | 27.6               | 132.2             |
+| [YOLO11x-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-seg.pt) | 640                   | 54.7                 | 43.8                  | 664.5 ± 3.2                    | 15.8 ± 0.7                          | 62.1               | 296.4             |
 
 - **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`
@@ -166,11 +166,11 @@ Consult the [Classification Docs](https://docs.ultralytics.com/tasks/classify/)
 
 | Model                                                                                        | size<br><sup>(pixels) | acc<br><sup>top1 | acc<br><sup>top5 | Speed<br><sup>CPU ONNX<br>(ms) | Speed<br><sup>T4 TensorRT10<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>(B) at 224 |
 | -------------------------------------------------------------------------------------------- | --------------------- | ---------------- | ---------------- | ------------------------------ | ----------------------------------- | ------------------ | ------------------------ |
-| [YOLO11n-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-cls.pt) | 224                   | 70.0             | 89.4             | 5.0 ± 0.3                      | 1.1 ± 0.0                           | 1.6                | 0.5                      |
-| [YOLO11s-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-cls.pt) | 224                   | 75.4             | 92.7             | 7.9 ± 0.2                      | 1.3 ± 0.0                           | 5.5                | 1.6                      |
-| [YOLO11m-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-cls.pt) | 224                   | 77.3             | 93.9             | 17.2 ± 0.4                     | 2.0 ± 0.0                           | 10.4               | 5.0                      |
-| [YOLO11l-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-cls.pt) | 224                   | 78.3             | 94.3             | 23.2 ± 0.3                     | 2.8 ± 0.0                           | 12.9               | 6.2                      |
-| [YOLO11x-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-cls.pt) | 224                   | 79.5             | 94.9             | 41.4 ± 0.9                     | 3.8 ± 0.0                           | 28.4               | 13.7                     |
+| [YOLO11n-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-cls.pt) | 224                   | 70.0             | 89.4             | 5.0 ± 0.3                      | 1.1 ± 0.0                           | 2.8                | 0.5                      |
+| [YOLO11s-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-cls.pt) | 224                   | 75.4             | 92.7             | 7.9 ± 0.2                      | 1.3 ± 0.0                           | 6.7                | 1.6                      |
+| [YOLO11m-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-cls.pt) | 224                   | 77.3             | 93.9             | 17.2 ± 0.4                     | 2.0 ± 0.0                           | 11.6               | 4.9                      |
+| [YOLO11l-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-cls.pt) | 224                   | 78.3             | 94.3             | 23.2 ± 0.3                     | 2.8 ± 0.0                           | 14.1               | 6.2                      |
+| [YOLO11x-cls](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-cls.pt) | 224                   | 79.5             | 94.9             | 41.4 ± 0.9                     | 3.8 ± 0.0                           | 29.6               | 13.6                     |
 
 - **acc** values represent model accuracy on the [ImageNet](https://www.image-net.org/) dataset validation set. <br>Reproduce with `yolo val classify data=path/to/ImageNet device=0`
 - **Speed** metrics are averaged over ImageNet 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 classify data=path/to/ImageNet batch=1 device=0|cpu`
@@ -183,11 +183,11 @@ 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) |
 | ---------------------------------------------------------------------------------------------- | --------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-pose.pt) | 640                   | 50.0                  | 81.0               | 52.4 ± 0.5                     | 1.7 ± 0.0                           | 2.9                | 7.6               |
-| [YOLO11s-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-pose.pt) | 640                   | 58.9                  | 86.3               | 90.5 ± 0.6                     | 2.6 ± 0.0                           | 9.9                | 23.2              |
-| [YOLO11m-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-pose.pt) | 640                   | 64.9                  | 89.4               | 187.3 ± 0.8                    | 4.9 ± 0.1                           | 20.9               | 71.7              |
-| [YOLO11l-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-pose.pt) | 640                   | 66.1                  | 89.9               | 247.7 ± 1.1                    | 6.4 ± 0.1                           | 26.2               | 90.7              |
-| [YOLO11x-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-pose.pt) | 640                   | 69.5                  | 91.1               | 488.0 ± 13.9                   | 12.1 ± 0.2                          | 58.8               | 203.3             |
+| [YOLO11n-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-pose.pt) | 640                   | 50.0                  | 81.0               | 52.4 ± 0.5                     | 1.7 ± 0.0                           | 2.9                | 7.4               |
+| [YOLO11s-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-pose.pt) | 640                   | 58.9                  | 86.3               | 90.5 ± 0.6                     | 2.6 ± 0.0                           | 9.9                | 23.1              |
+| [YOLO11m-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-pose.pt) | 640                   | 64.9                  | 89.4               | 187.3 ± 0.8                    | 4.9 ± 0.1                           | 20.9               | 71.4              |
+| [YOLO11l-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-pose.pt) | 640                   | 66.1                  | 89.9               | 247.7 ± 1.1                    | 6.4 ± 0.1                           | 26.1               | 90.3              |
+| [YOLO11x-pose](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-pose.pt) | 640                   | 69.5                  | 91.1               | 488.0 ± 13.9                   | 12.1 ± 0.2                          | 58.8               | 202.8             |
 
 - **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`
@@ -200,11 +200,11 @@ 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) |
 | -------------------------------------------------------------------------------------------- | --------------------- | ------------------ | ------------------------------ | ----------------------------------- | ------------------ | ----------------- |
-| [YOLO11n-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-obb.pt) | 1024                  | 78.4               | 117.6 ± 0.8                    | 4.4 ± 0.0                           | 2.7                | 17.2              |
-| [YOLO11s-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-obb.pt) | 1024                  | 79.5               | 219.4 ± 4.0                    | 5.1 ± 0.0                           | 9.7                | 57.5              |
-| [YOLO11m-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-obb.pt) | 1024                  | 80.9               | 562.8 ± 2.9                    | 10.1 ± 0.4                          | 20.9               | 183.5             |
-| [YOLO11l-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-obb.pt) | 1024                  | 81.0               | 712.5 ± 5.0                    | 13.5 ± 0.6                          | 26.2               | 232.0             |
-| [YOLO11x-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-obb.pt) | 1024                  | 81.3               | 1408.6 ± 7.7                   | 28.6 ± 1.0                          | 58.8               | 520.2             |
+| [YOLO11n-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n-obb.pt) | 1024                  | 78.4               | 117.6 ± 0.8                    | 4.4 ± 0.0                           | 2.7                | 16.8              |
+| [YOLO11s-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s-obb.pt) | 1024                  | 79.5               | 219.4 ± 4.0                    | 5.1 ± 0.0                           | 9.7                | 57.1              |
+| [YOLO11m-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11m-obb.pt) | 1024                  | 80.9               | 562.8 ± 2.9                    | 10.1 ± 0.4                          | 20.9               | 182.8             |
+| [YOLO11l-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11l-obb.pt) | 1024                  | 81.0               | 712.5 ± 5.0                    | 13.5 ± 0.6                          | 26.1               | 231.2             |
+| [YOLO11x-obb](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11x-obb.pt) | 1024                  | 81.3               | 1408.6 ± 7.7                   | 28.6 ± 1.0                          | 58.8               | 519.1             |
 
 - **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-8.3.203 → ultralytics-8.3.204}/pyproject.toml

@@ -158,9 +158,6 @@ source = ["ultralytics/"]
 data_file = "tests/.coverage"
 omit = ["ultralytics/utils/callbacks/*"]
 
-[tool.uv]
-required-version = "==0.8.19"
-
 [tool.isort]
 line_length = 120
 multi_line_output = 0

{ultralytics-8.3.203 → ultralytics-8.3.204}/tests/test_cli.py

@@ -34,7 +34,7 @@ def test_train(task: str, model: str, data: str) -> None:
 @pytest.mark.parametrize("task,model,data", TASK_MODEL_DATA)
 def test_val(task: str, model: str, data: str) -> None:
     """Test YOLO validation process for specified task, model, and data using a shell command."""
-    run(f"yolo val {task} model={model} data={data} imgsz=32 save_txt save_json")
+    run(f"yolo val {task} model={model} data={data} imgsz=32 save_txt save_json visualize")
 
 
 @pytest.mark.parametrize("task,model,data", TASK_MODEL_DATA)

{ultralytics-8.3.203 → ultralytics-8.3.204}/tests/test_cuda.py

@@ -70,6 +70,7 @@ def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
         simplify=simplify,
         nms=nms,
         device=DEVICES[0],
+        # opset=20 if nms else None,  # fix ONNX Runtime errors with NMS
     )
     YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, device=DEVICES[0])  # exported model inference
     Path(file).unlink()  # cleanup
@@ -114,7 +115,9 @@ def test_train():
     device = tuple(DEVICES) if len(DEVICES) > 1 else DEVICES[0]
     # NVIDIA Jetson only has one GPU and therefore skipping checks
     if not IS_JETSON:
-        results = YOLO(MODEL).train(data="coco8.yaml", imgsz=64, epochs=1, device=device)  # requires imgsz>=64
+        results = YOLO(MODEL).train(
+            data="coco8.yaml", imgsz=64, epochs=1, device=device, batch=15
+        )  # requires imgsz>=64
         visible = eval(os.environ["CUDA_VISIBLE_DEVICES"])
         assert visible == device, f"Passed GPUs '{device}', but used GPUs '{visible}'"
         assert (

{ultralytics-8.3.203 → ultralytics-8.3.204}/tests/test_exports.py

@@ -83,7 +83,7 @@ def test_export_openvino_matrix(task, dynamic, int8, half, batch, nms):
         for task, dynamic, int8, half, batch, simplify, nms in product(
             TASKS, [True, False], [False], [False], [1, 2], [True, False], [True, False]
         )
-        if not ((int8 and half) or (task == "classify" and nms) or (task == "obb" and nms and not TORCH_1_13))
+        if not ((int8 and half) or (task == "classify" and nms) or (nms and not TORCH_1_13))
     ],
 )
 def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
@@ -157,7 +157,7 @@ def test_export_coreml_matrix(task, dynamic, int8, half, nms, batch):
         for task, dynamic, int8, half, batch, nms in product(
             TASKS, [False], [True, False], [True, False], [1], [True, False]
         )
-        if not ((int8 and half) or (task == "classify" and nms) or (ARM64 and nms))
+        if not ((int8 and half) or (task == "classify" and nms) or (ARM64 and nms) or (nms and not TORCH_1_13))
     ],
 )
 def test_export_tflite_matrix(task, dynamic, int8, half, batch, nms):

{ultralytics-8.3.203 → ultralytics-8.3.204}/tests/test_python.py

@@ -673,7 +673,7 @@ def test_yoloe():
     model.val(data="coco128-seg.yaml", load_vp=True, imgsz=32)
 
     # Train, fine-tune
-    from ultralytics.models.yolo.yoloe import YOLOEPESegTrainer
+    from ultralytics.models.yolo.yoloe import YOLOEPESegTrainer, YOLOESegTrainerFromScratch
 
     model = YOLOE("yoloe-11s-seg.pt")
     model.train(
@@ -683,6 +683,15 @@ def test_yoloe():
         trainer=YOLOEPESegTrainer,
         imgsz=32,
     )
+    # Train, from scratch
+    model = YOLOE("yoloe-11s-seg.yaml")
+    model.train(
+        data=dict(train=dict(yolo_data=["coco128-seg.yaml"]), val=dict(yolo_data=["coco128-seg.yaml"])),
+        epochs=1,
+        close_mosaic=1,
+        trainer=YOLOESegTrainerFromScratch,
+        imgsz=32,
+    )
 
     # prompt-free
     # predict

{ultralytics-8.3.203 → ultralytics-8.3.204}/tests/test_solutions.py

@@ -12,8 +12,9 @@ import pytest
 
 from tests import MODEL, TMP
 from ultralytics import solutions
-from ultralytics.utils import ASSETS_URL, IS_RASPBERRYPI, checks
+from ultralytics.utils import ASSETS_URL, IS_RASPBERRYPI, TORCH_VERSION, checks
 from ultralytics.utils.downloads import safe_download
+from ultralytics.utils.torch_utils import TORCH_2_4
 
 # Pre-defined arguments values
 SHOW = False
@@ -205,15 +206,6 @@ def test_solution(name, solution_class, needs_frame_count, video, kwargs):
     )
 
 
-@pytest.mark.skipif(checks.IS_PYTHON_3_8, reason="Disabled due to unsupported CLIP dependencies.")
-@pytest.mark.skipif(IS_RASPBERRYPI, reason="Disabled due to slow performance on Raspberry Pi.")
-def test_similarity_search():
-    """Test similarity search solution with sample images and text query."""
-    safe_download(f"{ASSETS_URL}/4-imgs-similaritysearch.zip", dir=TMP)  # 4 dog images for testing in a zip file
-    searcher = solutions.VisualAISearch(data=str(TMP / "4-imgs-similaritysearch"))
-    _ = searcher("a dog sitting on a bench")  # Returns the results in format "- img name | similarity score"
-
-
 def test_left_click_selection():
     """Test distance calculation left click selection functionality."""
     dc = solutions.DistanceCalculation()
@@ -297,7 +289,16 @@ def test_streamlit_handle_video_upload_creates_file():
     os.remove("ultralytics.mp4")
 
 
-@pytest.mark.skipif(checks.IS_PYTHON_3_8, reason="Disabled due to unsupported CLIP dependencies.")
+@pytest.mark.skipif(not TORCH_2_4, reason=f"VisualAISearch requires torch>=2.4 (found torch=={TORCH_VERSION})")
+@pytest.mark.skipif(IS_RASPBERRYPI, reason="Disabled due to slow performance on Raspberry Pi.")
+def test_similarity_search():
+    """Test similarity search solution with sample images and text query."""
+    safe_download(f"{ASSETS_URL}/4-imgs-similaritysearch.zip", dir=TMP)  # 4 dog images for testing in a zip file
+    searcher = solutions.VisualAISearch(data=str(TMP / "4-imgs-similaritysearch"))
+    _ = searcher("a dog sitting on a bench")  # Returns the results in format "- img name | similarity score"
+
+
+@pytest.mark.skipif(not TORCH_2_4, reason=f"VisualAISearch requires torch>=2.4 (found torch=={TORCH_VERSION})")
 @pytest.mark.skipif(IS_RASPBERRYPI, reason="Disabled due to slow performance on Raspberry Pi.")
 def test_similarity_search_app_init():
     """Test SearchApp initializes with required attributes."""
@@ -306,6 +307,7 @@ def test_similarity_search_app_init():
     assert hasattr(app, "run")
 
 
+@pytest.mark.skipif(not TORCH_2_4, reason=f"VisualAISearch requires torch>=2.4 (found torch=={TORCH_VERSION})")
 @pytest.mark.skipif(IS_RASPBERRYPI, reason="Disabled due to slow performance on Raspberry Pi.")
 def test_similarity_search_complete(tmp_path):
     """Test VisualAISearch end-to-end with sample image and query."""

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.203"
+__version__ = "8.3.204"
 
 import importlib
 import os

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/data/utils.py

@@ -512,6 +512,11 @@ def check_cls_dataset(dataset: str | Path, split: str = "") -> dict[str, Any]:
     dataset = Path(dataset)
     data_dir = (dataset if dataset.is_dir() else (DATASETS_DIR / dataset)).resolve()
     if not data_dir.is_dir():
+        if data_dir.suffix != "":
+            raise ValueError(
+                f'Classification datasets must be a directory (data="path/to/dir") not a file (data="{dataset}"), '
+                "See https://docs.ultralytics.com/datasets/classify/"
+            )
         LOGGER.info("")
         LOGGER.warning(f"Dataset not found, missing path {data_dir}, attempting download...")
         t = time.time()

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/engine/exporter.py

@@ -112,7 +112,7 @@ from ultralytics.utils.metrics import batch_probiou
 from ultralytics.utils.nms import TorchNMS
 from ultralytics.utils.ops import Profile
 from ultralytics.utils.patches import arange_patch
-from ultralytics.utils.torch_utils import TORCH_1_11, TORCH_1_13, TORCH_2_1, select_device
+from ultralytics.utils.torch_utils import TORCH_1_11, TORCH_1_13, TORCH_2_1, TORCH_2_4, select_device
 
 
 def export_formats():
@@ -152,10 +152,13 @@ def export_formats():
     return dict(zip(["Format", "Argument", "Suffix", "CPU", "GPU", "Arguments"], zip(*x)))
 
 
-def best_onnx_opset(onnx) -> int:
+def best_onnx_opset(onnx, cuda=False) -> int:
     """Return max ONNX opset for this torch version with ONNX fallback."""
-    if TORCH_1_13:  # not supported by torch<1.13
+    version = ".".join(TORCH_VERSION.split(".")[:2])
+    if TORCH_2_4:  # _constants.ONNX_MAX_OPSET first defined in torch 1.13
         opset = torch.onnx.utils._constants.ONNX_MAX_OPSET - 1  # use second-latest version for safety
+        if cuda:
+            opset -= 2  # fix CUDA ONNXRuntime NMS squeeze op errors
     else:
         opset = {
             "1.8": 12,
@@ -164,16 +167,16 @@ def best_onnx_opset(onnx) -> int:
             "1.11": 14,
             "1.12": 15,
             "1.13": 17,
-            "2.0": 18,
-            "2.1": 19,
-            "2.2": 19,
-            "2.3": 19,
+            "2.0": 17,  # reduced from 18 to fix ONNX errors
+            "2.1": 17,  # reduced from 19
+            "2.2": 17,  # reduced from 19
+            "2.3": 17,  # reduced from 19
             "2.4": 20,
             "2.5": 20,
             "2.6": 20,
             "2.7": 20,
             "2.8": 23,
-        }.get(".".join(TORCH_VERSION.split(".")[:2]), 12)
+        }.get(version, 12)
     return min(opset, onnx.defs.onnx_opset_version())
 
 
@@ -380,6 +383,8 @@ class Exporter:
         if self.args.nms:
             assert not isinstance(model, ClassificationModel), "'nms=True' is not valid for classification models."
             assert not tflite or not ARM64 or not LINUX, "TFLite export with NMS unsupported on ARM64 Linux"
+            assert not is_tf_format or TORCH_1_13, "TensorFlow exports with NMS require torch>=1.13"
+            assert not onnx or TORCH_1_13, "ONNX export with NMS requires torch>=1.13"
             if getattr(model, "end2end", False):
                 LOGGER.warning("'nms=True' is not available for end2end models. Forcing 'nms=False'.")
                 self.args.nms = False
@@ -611,8 +616,11 @@ class Exporter:
         check_requirements(requirements)
         import onnx  # noqa
 
-        opset = self.args.opset or best_onnx_opset(onnx)
+        opset = self.args.opset or best_onnx_opset(onnx, cuda="cuda" in self.device.type)
         LOGGER.info(f"\n{prefix} starting export with onnx {onnx.__version__} opset {opset}...")
+        if self.args.nms:
+            assert TORCH_1_13, f"'nms=True' ONNX export requires torch>=1.13 (found torch=={TORCH_VERSION})"
+
         f = str(self.file.with_suffix(".onnx"))
         output_names = ["output0", "output1"] if isinstance(self.model, SegmentationModel) else ["output0"]
         dynamic = self.args.dynamic

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/engine/trainer.py

@@ -123,7 +123,7 @@ class BaseTrainer:
         self.hub_session = overrides.pop("session", None)  # HUB
         self.args = get_cfg(cfg, overrides)
         self.check_resume(overrides)
-        self.device = select_device(self.args.device, self.args.batch)
+        self.device = select_device(self.args.device)
         # Update "-1" devices so post-training val does not repeat search
         self.args.device = os.getenv("CUDA_VISIBLE_DEVICES") if "cuda" in str(self.device) else str(self.device)
         self.validator = None
@@ -216,10 +216,10 @@ class BaseTrainer:
                 LOGGER.warning("'rect=True' is incompatible with Multi-GPU training, setting 'rect=False'")
                 self.args.rect = False
             if self.args.batch < 1.0:
-                LOGGER.warning(
-                    "'batch<1' for AutoBatch is incompatible with Multi-GPU training, setting default 'batch=16'"
+                raise ValueError(
+                    "AutoBatch with batch<1 not supported for Multi-GPU training, "
+                    f"please specify a valid batch size multiple of GPU count {self.world_size}, i.e. batch={self.world_size * 8}."
                 )
-                self.args.batch = 16
 
             # Command
             cmd, file = generate_ddp_command(self)
@@ -260,10 +260,6 @@ class BaseTrainer:
         self.model = self.model.to(self.device)
         self.set_model_attributes()
 
-        # Initialize loss criterion before compilation for torch.compile compatibility
-        if hasattr(self.model, "init_criterion"):
-            self.model.criterion = self.model.init_criterion()
-
         # Compile model
         self.model = attempt_compile(self.model, device=self.device, mode=self.args.compile)
 

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/engine/validator.py

@@ -160,7 +160,7 @@ class BaseValidator:
             callbacks.add_integration_callbacks(self)
             model = AutoBackend(
                 model=model or self.args.model,
-                device=select_device(self.args.device, self.args.batch),
+                device=select_device(self.args.device),
                 dnn=self.args.dnn,
                 data=self.args.data,
                 fp16=self.args.half,

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/sam/modules/sam.py

@@ -712,7 +712,7 @@ class SAM2Model(torch.nn.Module):
                     continue  # skip padding frames
                 # "maskmem_features" might have been offloaded to CPU in demo use cases,
                 # so we load it back to inference device (it's a no-op if it's already on device).
-                feats = prev["maskmem_features"].to(device=device, non_blocking=True)
+                feats = prev["maskmem_features"].to(device=device, non_blocking=device.type == "cuda")
                 to_cat_memory.append(feats.flatten(2).permute(2, 0, 1))
                 # Spatial positional encoding (it might have been offloaded to CPU in eval)
                 maskmem_enc = prev["maskmem_pos_enc"][-1].to(device=device)

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/sam/predict.py

@@ -1126,7 +1126,9 @@ class SAM2VideoPredictor(SAM2Predictor):
             )
 
             if prev_out is not None and prev_out.get("pred_masks") is not None:
-                prev_sam_mask_logits = prev_out["pred_masks"].to(device=self.device, non_blocking=True)
+                prev_sam_mask_logits = prev_out["pred_masks"].to(
+                    device=self.device, non_blocking=self.device.type == "cuda"
+                )
                 # Clamp the scale of prev_sam_mask_logits to avoid rare numerical issues.
                 prev_sam_mask_logits.clamp_(-32.0, 32.0)
         current_out = self._run_single_frame_inference(
@@ -1418,12 +1420,12 @@ class SAM2VideoPredictor(SAM2Predictor):
         maskmem_features = current_out["maskmem_features"]
         if maskmem_features is not None:
             current_out["maskmem_features"] = maskmem_features.to(
-                dtype=torch.float16, device=self.device, non_blocking=True
+                dtype=torch.float16, device=self.device, non_blocking=self.device.type == "cuda"
             )
         # NOTE: Do not support the `fill_holes_in_mask_scores` function since it needs cuda extensions
         # potentially fill holes in the predicted masks
         # if self.fill_hole_area > 0:
-        #     pred_masks = current_out["pred_masks"].to(self.device, non_blocking=True)
+        #     pred_masks = current_out["pred_masks"].to(self.device, non_blocking=self.device.type == "cuda")
         #     pred_masks = fill_holes_in_mask_scores(pred_masks, self.fill_hole_area)
 
         # "maskmem_pos_enc" is the same across frames, so we only need to store one copy of it
@@ -1636,7 +1638,9 @@ class SAM2VideoPredictor(SAM2Predictor):
 
         # "maskmem_pos_enc" is the same across frames, so we only need to store one copy of it
         maskmem_pos_enc = self._get_maskmem_pos_enc(maskmem_pos_enc)
-        return maskmem_features.to(dtype=torch.float16, device=self.device, non_blocking=True), maskmem_pos_enc
+        return maskmem_features.to(
+            dtype=torch.float16, device=self.device, non_blocking=self.device.type == "cuda"
+        ), maskmem_pos_enc
 
     def _add_output_per_object(self, frame_idx, current_out, storage_key):
         """
@@ -1906,7 +1910,7 @@ class SAM2DynamicInteractivePredictor(SAM2Predictor):
                     consolidated_out["object_score_logits"][obj_idx : obj_idx + 1] = out["object_score_logits"]
 
         high_res_masks = F.interpolate(
-            consolidated_out["pred_masks"].to(self.device, non_blocking=True),
+            consolidated_out["pred_masks"].to(self.device, non_blocking=self.device.type == "cuda"),
             size=self.imgsz,
             mode="bilinear",
             align_corners=False,

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/classify/train.py

@@ -155,8 +155,8 @@ class ClassificationTrainer(BaseTrainer):
 
     def preprocess_batch(self, batch: dict[str, torch.Tensor]) -> dict[str, torch.Tensor]:
         """Preprocess a batch of images and classes."""
-        batch["img"] = batch["img"].to(self.device, non_blocking=True)
-        batch["cls"] = batch["cls"].to(self.device, non_blocking=True)
+        batch["img"] = batch["img"].to(self.device, non_blocking=self.device.type == "cuda")
+        batch["cls"] = batch["cls"].to(self.device, non_blocking=self.device.type == "cuda")
         return batch
 
     def progress_string(self) -> str:

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/classify/val.py

@@ -89,9 +89,9 @@ class ClassificationValidator(BaseValidator):
 
     def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
         """Preprocess input batch by moving data to device and converting to appropriate dtype."""
-        batch["img"] = batch["img"].to(self.device, non_blocking=True)
+        batch["img"] = batch["img"].to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = batch["img"].half() if self.args.half else batch["img"].float()
-        batch["cls"] = batch["cls"].to(self.device, non_blocking=True)
+        batch["cls"] = batch["cls"].to(self.device, non_blocking=self.device.type == "cuda")
         return batch
 
     def update_metrics(self, preds: torch.Tensor, batch: dict[str, Any]) -> None:

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/detect/train.py

@@ -120,7 +120,7 @@ class DetectionTrainer(BaseTrainer):
         """
         for k, v in batch.items():
             if isinstance(v, torch.Tensor):
-                batch[k] = v.to(self.device, non_blocking=True)
+                batch[k] = v.to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = batch["img"].float() / 255
         if self.args.multi_scale:
             imgs = batch["img"]

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/detect/val.py

@@ -73,7 +73,7 @@ class DetectionValidator(BaseValidator):
         """
         for k, v in batch.items():
             if isinstance(v, torch.Tensor):
-                batch[k] = v.to(self.device, non_blocking=True)
+                batch[k] = v.to(self.device, non_blocking=self.device.type == "cuda")
         batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
         return batch
 

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/model.py

@@ -416,6 +416,7 @@ class YOLOE(Model):
                         "batch": 1,
                         "device": kwargs.get("device", None),
                         "half": kwargs.get("half", False),
+                        "imgsz": kwargs.get("imgsz", self.overrides["imgsz"]),
                     },
                     _callbacks=self.callbacks,
                 )

{ultralytics-8.3.203 → ultralytics-8.3.204}/ultralytics/models/yolo/world/train.py

@@ -172,7 +172,8 @@ class WorldTrainer(DetectionTrainer):
 
         # Add text features
         texts = list(itertools.chain(*batch["texts"]))
-        txt_feats = torch.stack([self.text_embeddings[text] for text in texts]).to(self.device, non_blocking=True)
-        txt_feats = txt_feats / txt_feats.norm(p=2, dim=-1, keepdim=True)
+        txt_feats = torch.stack([self.text_embeddings[text] for text in texts]).to(
+            self.device, non_blocking=self.device.type == "cuda"
+        )
         batch["txt_feats"] = txt_feats.reshape(len(batch["texts"]), -1, txt_feats.shape[-1])
         return batch