[Model] Support YOLOv8 (#1137)

* add GPL lisence * add GPL-3.0 lisence * add GPL-3.0 lisence * add GPL-3.0 lisence * support yolov8 * add pybind for yolov8 * add yolov8 readme Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2025-10-05 16:48:03 +08:00 · 2023-01-16 11:24:23 +08:00
parent a4b94b2c93
commit 02bd22422e
28 changed files with 1448 additions and 80 deletions
--- a/examples/vision/detection/yolov8/python/README_CN.md
+++ b/examples/vision/detection/yolov8/python/README_CN.md
@@ -0,0 +1,78 @@
+[English](README.md) | 简体中文
+# YOLOv8 Python部署示例
+
+在部署前，需确认以下两个步骤
+
+- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)  
+- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
+
+本目录下提供`infer.py`快速完成YOLOv8在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
+
+```bash
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov8/python/
+
+#下载yolov8模型文件和测试图片
+wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov8.onnx
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+
+# CPU推理
+python infer.py --model yolov8.onnx --image 000000014439.jpg --device cpu
+# GPU推理
+python infer.py --model yolov8.onnx --image 000000014439.jpg --device gpu
+# GPU上使用TensorRT推理
+python infer.py --model yolov8.onnx --image 000000014439.jpg --device gpu --use_trt True
+```
+
+运行完成可视化结果如下图所示
+
+<img width="640" src="https://user-images.githubusercontent.com/67993288/184309358-d803347a-8981-44b6-b589-4608021ad0f4.jpg">
+
+## YOLOv8 Python接口
+
+```python
+fastdeploy.vision.detection.YOLOv8(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.ONNX)
+```
+
+YOLOv8模型加载和初始化，其中model_file为导出的ONNX模型格式
+
+**参数**
+
+> * **model_file**(str): 模型文件路径
+> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
+> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
+> * **model_format**(ModelFormat): 模型格式，默认为ONNX
+
+### predict函数
+
+> ```python
+> YOLOv8.predict(image_data)
+> ```
+>
+> 模型预测结口，输入图像直接输出检测结果。
+>
+> **参数**
+>
+> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
+
+> **返回**
+>
+> > 返回`fastdeploy.vision.DetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
+
+### 类成员属性
+#### 预处理参数
+用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
+
+> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
+> > * **padding_value**(list[float]): 通过此参数可以修改图片在resize时候做填充(padding)的值, 包含三个浮点型元素, 分别表示三个通道的值, 默认值为[114, 114, 114]
+> > * **is_no_pad**(bool): 通过此参数让图片是否通过填充的方式进行resize, `is_no_pad=True` 表示不使用填充的方式，默认值为`is_no_pad=False`
+> > * **is_mini_pad**(bool): 通过此参数可以将resize之后图像的宽高这是为最接近`size`成员变量的值, 并且满足填充的像素大小是可以被`stride`成员变量整除的。默认值为`is_mini_pad=False`
+> > * **stride**(int): 配合`stris_mini_padide`成员变量使用, 默认值为`stride=32`
+
+## 其它文档
+
+- [YOLOv8 模型介绍](..)
+- [YOLOv8 C++部署](../cpp)
+- [模型预测结果说明](../../../../../docs/api/vision_results/)
+- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
--- a/examples/vision/detection/yolov8/python/infer.py
+++ b/examples/vision/detection/yolov8/python/infer.py
@@ -0,0 +1,58 @@
+import fastdeploy as fd
+import cv2
+import os
+
+
+def parse_arguments():
+    import argparse
+    import ast
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model", default=None, help="Path of yolov8 model.")
+    parser.add_argument(
+        "--image", default=None, help="Path of test image file.")
+    parser.add_argument(
+        "--device",
+        type=str,
+        default='cpu',
+        help="Type of inference device, support 'cpu' or 'gpu' or 'kunlunxin'.")
+    parser.add_argument(
+        "--use_trt",
+        type=ast.literal_eval,
+        default=False,
+        help="Wether to use tensorrt.")
+    return parser.parse_args()
+
+
+def build_option(args):
+    option = fd.RuntimeOption()
+
+    if args.device.lower() == "gpu":
+        option.use_gpu()
+
+    if args.device.lower() == "ascend":
+        option.use_ascend()
+
+    if args.use_trt:
+        option.use_trt_backend()
+        option.set_trt_input_shape("images", [1, 3, 640, 640])
+    return option
+
+
+args = parse_arguments()
+
+# Configure runtime, load model
+runtime_option = build_option(args)
+model = fd.vision.detection.YOLOv8(args.model, runtime_option=runtime_option)
+
+# Predicting image
+if args.image is None:
+    image = fd.utils.get_detection_test_image()
+else:
+    image = args.image
+im = cv2.imread(image)
+result = model.predict(im)
+
+# Visualization
+vis_im = fd.vision.vis_detection(im, result)
+cv2.imwrite("visualized_result.jpg", vis_im)
+print("Visualized result save in ./visualized_result.jpg")