xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-23 21:44:22 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix undefined ‘im_array’ bug in predict.md (#8565)

Browse Source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: fang_chenfang <1217690899@qq.com>
This commit is contained in:
Glenn Jocher 2024-03-01 00:53:17 +01:00 committed by GitHub
parent aa592efda5
commit 6bdf8dfaa2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
13 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/en/guides/model-deployment-options.md
View File

@ -240,9 +240,9 @@ PaddlePaddle is an open-source deep learning framework developed by Baidu. It is
- **Hardware Acceleration**: Supports various hardware accelerations, including Baidu's own Kunlun chips. - **Hardware Acceleration**: Supports various hardware accelerations, including Baidu's own Kunlun chips.
#### ncnn #### NCNN
ncnn is a high-performance neural network inference framework optimized for the mobile platform. It stands out for its lightweight nature and efficiency, making it particularly well-suited for mobile and embedded devices where resources are limited. NCNN is a high-performance neural network inference framework optimized for the mobile platform. It stands out for its lightweight nature and efficiency, making it particularly well-suited for mobile and embedded devices where resources are limited.
- **Performance Benchmarks**: Highly optimized for mobile platforms, offering efficient inference on ARM-based devices. - **Performance Benchmarks**: Highly optimized for mobile platforms, offering efficient inference on ARM-based devices.
@ -276,7 +276,7 @@ The following table provides a snapshot of the various deployment options availa
| TF Edge TPU | Optimized for Google's Edge TPU hardware | Exclusive to Edge TPU devices | Growing with Google and third-party resources | IoT devices requiring real-time processing | Improvements for new Edge TPU hardware | Google's robust IoT security | Custom-designed for Google Coral | | TF Edge TPU | Optimized for Google's Edge TPU hardware | Exclusive to Edge TPU devices | Growing with Google and third-party resources | IoT devices requiring real-time processing | Improvements for new Edge TPU hardware | Google's robust IoT security | Custom-designed for Google Coral |
| TF.js | Reasonable in-browser performance | High with web technologies | Web and Node.js developers support | Interactive web applications | TensorFlow team and community contributions | Web platform security model | Enhanced with WebGL and other APIs | | TF.js | Reasonable in-browser performance | High with web technologies | Web and Node.js developers support | Interactive web applications | TensorFlow team and community contributions | Web platform security model | Enhanced with WebGL and other APIs |
| PaddlePaddle | Competitive, easy to use and scalable | Baidu ecosystem, wide application support | Rapidly growing, especially in China | Chinese market and language processing | Focus on Chinese AI applications | Emphasizes data privacy and security | Including Baidu's Kunlun chips | | PaddlePaddle | Competitive, easy to use and scalable | Baidu ecosystem, wide application support | Rapidly growing, especially in China | Chinese market and language processing | Focus on Chinese AI applications | Emphasizes data privacy and security | Including Baidu's Kunlun chips |
| ncnn | Optimized for mobile ARM-based devices | Mobile and embedded ARM systems | Niche but active mobile/embedded ML community | Android and ARM systems efficiency | High performance maintenance on ARM | On-device security advantages | ARM CPUs and GPUs optimizations | | NCNN | Optimized for mobile ARM-based devices | Mobile and embedded ARM systems | Niche but active mobile/embedded ML community | Android and ARM systems efficiency | High performance maintenance on ARM | On-device security advantages | ARM CPUs and GPUs optimizations |
This comparative analysis gives you a high-level overview. For deployment, it's essential to consider the specific requirements and constraints of your project, and consult the detailed documentation and resources available for each option. This comparative analysis gives you a high-level overview. For deployment, it's essential to consider the specific requirements and constraints of your project, and consult the detailed documentation and resources available for each option.

2
docs/en/modes/benchmark.md
View File

@ -101,6 +101,6 @@ Benchmarks will attempt to run automatically on all possible export formats belo
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/modes/export.md
View File

@ -108,4 +108,4 @@ Available YOLOv8 export formats are in the table below. You can export to any fo
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` |

2
docs/en/modes/predict.md
View File

@ -683,7 +683,7 @@ The `plot()` method in `Results` objects facilitates visualization of prediction
for i, r in enumerate(results): for i, r in enumerate(results):
# Plot results image # Plot results image
im_bgr = r.plot() # BGR-order numpy array im_bgr = r.plot() # BGR-order numpy array
im_rgb = Image.fromarray(im_array[..., ::-1]) # RGB-order PIL image im_rgb = Image.fromarray(im_bgr[..., ::-1]) # RGB-order PIL image
# Show results to screen (in supported environments) # Show results to screen (in supported environments)
r.show() r.show()

2
docs/en/tasks/classify.md
View File

@ -176,6 +176,6 @@ Available YOLOv8-cls export formats are in the table below. You can predict or v
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-cls_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-cls_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-cls_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-cls_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-cls_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-cls_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/tasks/detect.md
View File

@ -177,6 +177,6 @@ Available YOLOv8 export formats are in the table below. You can predict or valid
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/tasks/obb.md
View File

@ -186,6 +186,6 @@ Available YOLOv8-obb export formats are in the table below. You can predict or v
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-obb_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-obb_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-obb_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-obb_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-obb_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-obb_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-obb_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-obb_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/tasks/pose.md
View File

@ -180,6 +180,6 @@ Available YOLOv8-pose export formats are in the table below. You can predict or
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-pose_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-pose_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-pose_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-pose_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-pose_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-pose_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-pose_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-pose_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/tasks/segment.md
View File

@ -182,6 +182,6 @@ Available YOLOv8-seg export formats are in the table below. You can predict or v
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-seg_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n-seg_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n-seg_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n-seg_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-seg_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n-seg_ncnn_model/` | ✅ | `imgsz`, `half` |
See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page. See full `export` details in the [Export](https://docs.ultralytics.com/modes/export/) page.

2
docs/en/usage/cli.md
View File

@ -184,7 +184,7 @@ Available YOLOv8 export formats are in the table below. You can export to any fo
| [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` | | [TF Edge TPU](https://coral.ai/docs/edgetpu/models-intro/) | `edgetpu` | `yolov8n_edgetpu.tflite` | ✅ | `imgsz` |
| [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` | | [TF.js](https://www.tensorflow.org/js) | `tfjs` | `yolov8n_web_model/` | ✅ | `imgsz`, `half`, `int8` |
| [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` | | [PaddlePaddle](https://github.com/PaddlePaddle) | `paddle` | `yolov8n_paddle_model/` | ✅ | `imgsz` |
| [ncnn](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` | | [NCNN](https://github.com/Tencent/ncnn) | `ncnn` | `yolov8n_ncnn_model/` | ✅ | `imgsz`, `half` |
## Overriding default arguments ## Overriding default arguments

10
ultralytics/engine/exporter.py
View File

@ -16,7 +16,7 @@ TensorFlow Lite | `tflite` | yolov8n.tflite
TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite
TensorFlow.js | `tfjs` | yolov8n_web_model/ TensorFlow.js | `tfjs` | yolov8n_web_model/
PaddlePaddle | `paddle` | yolov8n_paddle_model/ PaddlePaddle | `paddle` | yolov8n_paddle_model/
ncnn | `ncnn` | yolov8n_ncnn_model/ NCNN | `ncnn` | yolov8n_ncnn_model/
Requirements: Requirements:
$ pip install "ultralytics[export]" $ pip install "ultralytics[export]"
@ -293,7 +293,7 @@ class Exporter:
f[9], _ = self.export_tfjs() f[9], _ = self.export_tfjs()
if paddle: # PaddlePaddle if paddle: # PaddlePaddle
f[10], _ = self.export_paddle() f[10], _ = self.export_paddle()
if ncnn: # ncnn if ncnn: # NCNN
f[11], _ = self.export_ncnn() f[11], _ = self.export_ncnn()
# Finish # Finish
@ -496,14 +496,14 @@ class Exporter:
return f, None return f, None
@try_export @try_export
def export_ncnn(self, prefix=colorstr("ncnn:")): def export_ncnn(self, prefix=colorstr("NCNN:")):
""" """
YOLOv8 ncnn export using PNNX https://github.com/pnnx/pnnx. YOLOv8 NCNN export using PNNX https://github.com/pnnx/pnnx.
""" """
check_requirements("ncnn") check_requirements("ncnn")
import ncnn # noqa import ncnn # noqa
LOGGER.info(f"\n{prefix} starting export with ncnn {ncnn.__version__}...") LOGGER.info(f"\n{prefix} starting export with NCNN {ncnn.__version__}...")
f = Path(str(self.file).replace(self.file.suffix, f"_ncnn_model{os.sep}")) f = Path(str(self.file).replace(self.file.suffix, f"_ncnn_model{os.sep}"))
f_ts = self.file.with_suffix(".torchscript") f_ts = self.file.with_suffix(".torchscript")

10
ultralytics/nn/autobackend.py
View File

@ -72,7 +72,7 @@ class AutoBackend(nn.Module):
| TensorFlow Lite | *.tflite | | TensorFlow Lite | *.tflite |
| TensorFlow Edge TPU | *_edgetpu.tflite | | TensorFlow Edge TPU | *_edgetpu.tflite |
| PaddlePaddle | *_paddle_model | | PaddlePaddle | *_paddle_model |
| ncnn | *_ncnn_model | | NCNN | *_ncnn_model |
This class offers dynamic backend switching capabilities based on the input model format, making it easier to deploy This class offers dynamic backend switching capabilities based on the input model format, making it easier to deploy
models across various platforms. models across various platforms.
@ -304,9 +304,9 @@ class AutoBackend(nn.Module):
input_handle = predictor.get_input_handle(predictor.get_input_names()[0]) input_handle = predictor.get_input_handle(predictor.get_input_names()[0])
output_names = predictor.get_output_names() output_names = predictor.get_output_names()
metadata = w.parents[1] / "metadata.yaml" metadata = w.parents[1] / "metadata.yaml"
elif ncnn: # ncnn elif ncnn: # NCNN
LOGGER.info(f"Loading {w} for ncnn inference...") LOGGER.info(f"Loading {w} for NCNN inference...")
check_requirements("git+https://github.com/Tencent/ncnn.git" if ARM64 else "ncnn") # requires ncnn check_requirements("git+https://github.com/Tencent/ncnn.git" if ARM64 else "ncnn") # requires NCNN
import ncnn as pyncnn import ncnn as pyncnn
net = pyncnn.Net() net = pyncnn.Net()
@ -431,7 +431,7 @@ class AutoBackend(nn.Module):
self.input_handle.copy_from_cpu(im) self.input_handle.copy_from_cpu(im)
self.predictor.run() self.predictor.run()
y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names] y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names]
elif self.ncnn: # ncnn elif self.ncnn: # NCNN
mat_in = self.pyncnn.Mat(im[0].cpu().numpy()) mat_in = self.pyncnn.Mat(im[0].cpu().numpy())
ex = self.net.create_extractor() ex = self.net.create_extractor()
input_names, output_names = self.net.input_names(), self.net.output_names() input_names, output_names = self.net.input_names(), self.net.output_names()

2
ultralytics/utils/benchmarks.py
View File

@ -21,7 +21,7 @@ TensorFlow Lite | `tflite` | yolov8n.tflite
TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite TensorFlow Edge TPU | `edgetpu` | yolov8n_edgetpu.tflite
TensorFlow.js | `tfjs` | yolov8n_web_model/ TensorFlow.js | `tfjs` | yolov8n_web_model/
PaddlePaddle | `paddle` | yolov8n_paddle_model/ PaddlePaddle | `paddle` | yolov8n_paddle_model/
ncnn | `ncnn` | yolov8n_ncnn_model/ NCNN | `ncnn` | yolov8n_ncnn_model/
""" """
import glob import glob