xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-24 06:07:03 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

ultralytics 8.0.125 NMS speed improvements (#3463)

Browse Source 
Co-authored-by: Compunet <117437050+dme-compunet@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-07-03 16:34:13 +02:00 committed by GitHub
parent 0e5a6b8158
commit 8a11eda4a9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docs/datasets/segment/index.md
View File

@ -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 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 ### Dataset YAML format

2
examples/README.md
View File

@ -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 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 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) | | [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 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) | | [YOLOv8 ONNXRuntime Python](./YOLOv8-ONNXRuntime) | Python/ONNXRuntime | [Semih Demirel](https://github.com/semihhdemirel) |

2
ultralytics/__init__.py
View File

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

2
ultralytics/nn/autobackend.py
View File

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

2
ultralytics/yolo/engine/exporter.py
View File

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

4
ultralytics/yolo/utils/ops.py
View File

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