YOLOv9-Openvino和ONNXRuntime推理【CPU】

1 环境：

CPU：i5-12500
Python：3.8.18

2 安装Openvino和ONNXRuntime

2.1 Openvino简介

Openvino是由Intel开发的专门用于优化和部署人工智能推理的半开源的工具包，主要用于对深度推理做优化。

Openvino内部集成了Opencv、TensorFlow模块，除此之外它还具有强大的Plugin开发框架，允许开发者在Openvino之上对推理过程做优化。

Openvino整体框架为：Openvino前端→ Plugin中间层→ Backend后端
Openvino的优点在于它屏蔽了后端接口，提供了统一操作的前端API，开发者可以无需关心后端的实现，例如后端可以是TensorFlow、Keras、ARM-NN，通过Plugin提供给前端接口调用，也就意味着一套代码在Openvino之上可以运行在多个推理引擎之上，Openvino像是类似聚合一样的开发包。

2.2 ONNXRuntime简介

ONNXRuntime是微软推出的一款推理框架，用户可以非常便利的用其运行一个onnx模型。ONNXRuntime支持多种运行后端包括CPU，GPU，TensorRT，DML等。可以说ONNXRuntime是对ONNX模型最原生的支持。

虽然大家用ONNX时更多的是作为一个中间表示，从pytorch转到onnx后直接喂到TensorRT或MNN等各种后端框架，但这并不能否认ONNXRuntime是一款非常优秀的推理框架。而且由于其自身只包含推理功能（最新的ONNXRuntime甚至已经可以训练），通过阅读其源码可以解深度学习框架的一些核心功能原理（op注册，内存管理，运行逻辑等）
总体来看，整个ONNXRuntime的运行可以分为三个阶段，Session构造，模型加载与初始化和运行。和其他所有主流框架相同，ONNXRuntime最常用的语言是python，而实际负责执行框架运行的则是C++。

2.3 安装

pip install openvino -i  https://pypi.tuna.tsinghua.edu.cn/simple
pip install onnxruntime -i  https://pypi.tuna.tsinghua.edu.cn/simple

3 YOLOv9介绍

YOLOv9速读
文章地址：https://arxiv.org/pdf/2402.13616.pdf
Github：https://github.com/WongKinYiu/yolov9

4 基于Openvino和ONNXRuntime推理

下面代码整个处理过程主要包括：预处理—>推理—>后处理—>画图。
假设图像resize为640×640，
前处理输出结果维度：(1, 3, 640, 640)；
推理输出结果维度：(1, 84, 8400)，其中84表示4个box坐标信息+80个类别概率，8400表示80×80+40×40+20×20；
后处理输出结果维度：(5, 6)，其中第一个5表示图bus.jpg检出5个目标，第二个维度6表示(x1, y1, x2, y2, conf, cls)。
注：与YOLOv8输出维度一致，可通用！！！

4.1 全部代码

import argparse
import time 
import cv2
import numpy as np
from openvino.runtime import Core  # pip install openvino -i  https://pypi.tuna.tsinghua.edu.cn/simple
import onnxruntime as ort  # 使用onnxruntime推理用上，pip install onnxruntime，默认安装CPU# COCO默认的80类
CLASSES = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light','fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow','elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee','skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard','tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich','orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed','dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven','toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush']class OpenvinoInference(object):def __init__(self, onnx_path):self.onnx_path = onnx_pathie = Core()self.model_onnx = ie.read_model(model=self.onnx_path)self.compiled_model_onnx = ie.compile_model(model=self.model_onnx, device_name="CPU")self.output_layer_onnx = self.compiled_model_onnx.output(0)def predirts(self, datas):predict_data = self.compiled_model_onnx([datas])[self.output_layer_onnx]return predict_dataclass YOLOv9:"""YOLOv9 object detection model class for handling inference and visualization."""def __init__(self, onnx_model, imgsz=(640, 640), infer_tool='openvino'):"""Initialization.Args:onnx_model (str): Path to the ONNX model."""self.infer_tool = infer_toolif self.infer_tool == 'openvino':# 构建openvino推理引擎self.openvino = OpenvinoInference(onnx_model)self.ndtype = np.singleelse:# 构建onnxruntime推理引擎self.ort_session = ort.InferenceSession(onnx_model,providers=['CUDAExecutionProvider', 'CPUExecutionProvider']if ort.get_device() == 'GPU' else ['CPUExecutionProvider'])# Numpy dtype: support both FP32 and FP16 onnx modelself.ndtype = np.half if self.ort_session.get_inputs()[0].type == 'tensor(float16)' else np.singleself.classes = CLASSES  # 加载模型类别self.model_height, self.model_width = imgsz[0], imgsz[1]  # 图像resize大小self.color_palette = np.random.uniform(0, 255, size=(len(self.classes), 3))  # 为每个类别生成调色板def __call__(self, im0, conf_threshold=0.4, iou_threshold=0.45):"""The whole pipeline: pre-process -> inference -> post-process.Args:im0 (Numpy.ndarray): original input image.conf_threshold (float): confidence threshold for filtering predictions.iou_threshold (float): iou threshold for NMS.Returns:boxes (List): list of bounding boxes."""# 前处理Pre-processt1 = time.time()im, ratio, (pad_w, pad_h) = self.preprocess(im0)print('预处理时间：{:.3f}s'.format(time.time() - t1))# 推理 inferencet2 = time.time()if self.infer_tool == 'openvino':preds = self.openvino.predirts(im)else:preds = self.ort_session.run(None, {self.ort_session.get_inputs()[0].name: im})[0]print('推理时间：{:.2f}s'.format(time.time() - t2))# 后处理Post-processt3 = time.time()boxes = self.postprocess(preds,im0=im0,ratio=ratio,pad_w=pad_w,pad_h=pad_h,conf_threshold=conf_threshold,iou_threshold=iou_threshold,)print('后处理时间：{:.3f}s'.format(time.time() - t3))return boxes# 前处理，包括：resize, pad, HWC to CHW，BGR to RGB，归一化，增加维度CHW -> BCHWdef preprocess(self, img):"""Pre-processes the input image.Args:img (Numpy.ndarray): image about to be processed.Returns:img_process (Numpy.ndarray): image preprocessed for inference.ratio (tuple): width, height ratios in letterbox.pad_w (float): width padding in letterbox.pad_h (float): height padding in letterbox."""# Resize and pad input image using letterbox() (Borrowed from Ultralytics)shape = img.shape[:2]  # original image shapenew_shape = (self.model_height, self.model_width)r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])ratio = r, rnew_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))pad_w, pad_h = (new_shape[1] - new_unpad[0]) / 2, (new_shape[0] - new_unpad[1]) / 2  # wh paddingif shape[::-1] != new_unpad:  # resizeimg = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)top, bottom = int(round(pad_h - 0.1)), int(round(pad_h + 0.1))left, right = int(round(pad_w - 0.1)), int(round(pad_w + 0.1))img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114))  # 填充# Transforms: HWC to CHW -> BGR to RGB -> div(255) -> contiguous -> add axis(optional)img = np.ascontiguousarray(np.einsum('HWC->CHW', img)[::-1], dtype=self.ndtype) / 255.0img_process = img[None] if len(img.shape) == 3 else imgreturn img_process, ratio, (pad_w, pad_h)# 后处理，包括：阈值过滤与NMSdef postprocess(self, preds, im0, ratio, pad_w, pad_h, conf_threshold, iou_threshold):"""Post-process the prediction.Args:preds (Numpy.ndarray): predictions come from ort.session.run().im0 (Numpy.ndarray): [h, w, c] original input image.ratio (tuple): width, height ratios in letterbox.pad_w (float): width padding in letterbox.pad_h (float): height padding in letterbox.conf_threshold (float): conf threshold.iou_threshold (float): iou threshold.Returns:boxes (List): list of bounding boxes."""x = preds  # outputs: predictions (1, 84, 8400)# Transpose the first output: (Batch_size, xywh_conf_cls, Num_anchors) -> (Batch_size, Num_anchors, xywh_conf_cls)x = np.einsum('bcn->bnc', x)  # (1, 8400, 84)# Predictions filtering by conf-thresholdx = x[np.amax(x[..., 4:], axis=-1) > conf_threshold]# Create a new matrix which merge these(box, score, cls) into one# For more details about `numpy.c_()`: https://numpy.org/doc/1.26/reference/generated/numpy.c_.htmlx = np.c_[x[..., :4], np.amax(x[..., 4:], axis=-1), np.argmax(x[..., 4:], axis=-1)]# NMS filtering# 经过NMS后的值, np.array([[x, y, w, h, conf, cls], ...]), shape=(-1, 4 + 1 + 1)x = x[cv2.dnn.NMSBoxes(x[:, :4], x[:, 4], conf_threshold, iou_threshold)]# 重新缩放边界框，为画图做准备if len(x) > 0:# Bounding boxes format change: cxcywh -> xyxyx[..., [0, 1]] -= x[..., [2, 3]] / 2x[..., [2, 3]] += x[..., [0, 1]]# Rescales bounding boxes from model shape(model_height, model_width) to the shape of original imagex[..., :4] -= [pad_w, pad_h, pad_w, pad_h]x[..., :4] /= min(ratio)# Bounding boxes boundary clampx[..., [0, 2]] = x[:, [0, 2]].clip(0, im0.shape[1])x[..., [1, 3]] = x[:, [1, 3]].clip(0, im0.shape[0])return x[..., :6]  # boxeselse:return []# 绘框def draw_and_visualize(self, im, bboxes, vis=False, save=True):"""Draw and visualize results.Args:im (np.ndarray): original image, shape [h, w, c].bboxes (numpy.ndarray): [n, 4], n is number of bboxes.vis (bool): imshow using OpenCV.save (bool): save image annotated.Returns:None"""# Draw rectangles for (*box, conf, cls_) in bboxes:# draw bbox rectanglecv2.rectangle(im, (int(box[0]), int(box[1])), (int(box[2]), int(box[3])),self.color_palette[int(cls_)], 1, cv2.LINE_AA)cv2.putText(im, f'{self.classes[int(cls_)]}: {conf:.3f}', (int(box[0]), int(box[1] - 9)),cv2.FONT_HERSHEY_SIMPLEX, 0.7, self.color_palette[int(cls_)], 2, cv2.LINE_AA)# Show imageif vis:cv2.imshow('demo', im)cv2.waitKey(0)cv2.destroyAllWindows()# Save imageif save:cv2.imwrite('demo.jpg', im)if __name__ == '__main__':# Create an argument parser to handle command-line argumentsparser = argparse.ArgumentParser()parser.add_argument('--model', type=str, default='yolov9c.onnx', help='Path to ONNX model')parser.add_argument('--source', type=str, default=str('bus.jpg'), help='Path to input image')parser.add_argument('--imgsz', type=tuple, default=(640, 640), help='Image input size')parser.add_argument('--conf', type=float, default=0.25, help='Confidence threshold')parser.add_argument('--iou', type=float, default=0.45, help='NMS IoU threshold')parser.add_argument('--infer_tool', type=str, default='openvino', choices=("openvino", "onnxruntime"), help='选择推理引擎')args = parser.parse_args()# Build modelmodel = YOLOv9(args.model, args.imgsz, args.infer_tool)# Read image by OpenCVimg = cv2.imread(args.source)# Inferenceboxes = model(img, conf_threshold=args.conf, iou_threshold=args.iou)# Visualizeif len(boxes) > 0:model.draw_and_visualize(img, boxes, vis=False, save=True)