`ultralytics 8.0.125` NMS speed improvements (#3463)

Co-authored-by: Compunet <117437050+dme-compunet@users.noreply.github.com>

docs/datasets/segment/index.md

@@ -35,7 +35,10 @@ Here is an example of the YOLO dataset format for a single image with two object
 1 0.5046 0.0 0.5015 0.004 0.4984 0.00416 0.4937 0.010 0.492 0.0104
 ```
 
-Note: The length of each row does not have to be equal.
+!!! tip "Tip"
+
+      - The length of each row does not have to be equal.
+      - Each segmentation label must have a **minimum of 3 xy points**: `<class-index> <x1> <y1> <x2> <y2> <x3> <y3>`
 
 ### Dataset YAML format
 

examples/README.md

@@ -8,7 +8,7 @@ This repository features a collection of real-world applications and walkthrough
 | -------------------------------------------------------------------------------------------------------------- | ------------------ | --------------------------------------------------- |
 | [YOLO ONNX Detection Inference with C++](./YOLOv8-CPP-Inference)                                               | C++/ONNX           | [Justas Bartnykas](https://github.com/JustasBart)   |
 | [YOLO OpenCV ONNX Detection Python](./YOLOv8-OpenCV-ONNX-Python)                                               | OpenCV/Python/ONNX | [Farid Inawan](https://github.com/frdteknikelektro) |
-| [YOLO .NET ONNX ImageSharp](https://github.com/dme-compunet/YOLOv8)                                            | C#/ONNX/ImageSharp | [Compuet](https://github.com/dme-compunet)          |
+| [YOLOv8 .NET ONNX ImageSharp](https://github.com/dme-compunet/YOLOv8)                                          | C#/ONNX/ImageSharp | [Compunet](https://github.com/dme-compunet)         |
 | [YOLO .Net ONNX Detection C#](https://www.nuget.org/packages/Yolov8.Net)                                       | C# .Net            | [Samuel Stainback](https://github.com/sstainba)     |
 | [YOLOv8 on NVIDIA Jetson(TensorRT and DeepStream)](https://wiki.seeedstudio.com/YOLOv8-DeepStream-TRT-Jetson/) | Python             | [Lakshantha](https://github.com/lakshanthad)        |
 | [YOLOv8 ONNXRuntime Python](./YOLOv8-ONNXRuntime)                                                              | Python/ONNXRuntime | [Semih Demirel](https://github.com/semihhdemirel)   |

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = '8.0.124'
+__version__ = '8.0.125'
 
 from ultralytics.hub import start
 from ultralytics.vit.rtdetr import RTDETR

ultralytics/nn/autobackend.py

@@ -340,7 +340,7 @@ class AutoBackend(nn.Module):
         elif self.coreml:  # CoreML
             im = im[0].cpu().numpy()
             im_pil = Image.fromarray((im * 255).astype('uint8'))
-            # im = im.resize((192, 320), Image.ANTIALIAS)
+            # im = im.resize((192, 320), Image.BILINEAR)
             y = self.model.predict({'image': im_pil})  # coordinates are xywh normalized
             if 'confidence' in y:
                 box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels

ultralytics/yolo/engine/exporter.py

@@ -447,7 +447,7 @@ class Exporter:
                 check_requirements('nvidia-tensorrt', cmds='-U --index-url https://pypi.ngc.nvidia.com')
             import tensorrt as trt  # noqa
 
-        check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=8.0.0
+        check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
         self.args.simplify = True
         f_onnx, _ = self.export_onnx()
 

ultralytics/yolo/utils/ops.py

@@ -200,8 +200,7 @@ def non_max_suppression(
     multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)
     merge = False  # use merge-NMS
 
-    prediction = prediction.clone()  # don't modify original
+    prediction = prediction.transpose(-1, -2)  # shape(1,84,6300) to shape(1,6300,84)
-    prediction = prediction.transpose(-1, -2)  # to (batch, boxes, items)
     prediction[..., :4] = xywh2xyxy(prediction[..., :4])  # xywh to xyxy
 
     t = time.time()
@@ -245,7 +244,6 @@ def non_max_suppression(
         n = x.shape[0]  # number of boxes
         if not n:  # no boxes
             continue
-
         if n > max_nms:  # excess boxes
             x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence and remove excess boxes