当前位置： 首页 > news >正文

yolov5s.onnx转rk模型以及相关使用详细教程

news 2025/8/20 14:32:04

模型转换教程：YOLOv5从.pt到.rknn的详细步骤_pt转rknn-CSDN博客

（转rk模型需要onnx模型先进行裁剪，具体步骤看这一篇，如果想使用本文的导出检测方案和后续进行c++版本的改造的话，就需要在该文文章的裁剪处进行这样的处理）

 z.append(self.m[i](x[i]))#他的文章使用了sigmoid

1.yolov5s.onnx模型转rk模型

完整代码简介，这部分代码进行了onnx模型到rk模型的转化，并且给了一份用pythonAPI使用这个rk模型的测试代码。

1.1需要改的环境和配置参数（完整代码后面给）

1.1 环境前提

首先你需要有一个 rknn-toolkit2环境（ NPU（神经网络处理器）的模型转换与部署工具包）

下载完放置到liunx系统中，然后使用

docker load --input rknn-toolkit2-v2.3.0-cp38-docker.tar.gz

这个指令将镜像文件加载到本地 Docker 环境中

接着使用这两个指令

1.创建并使用该容器

  • -v 参数用于将主机的目录挂载到容器中，实现文件共享（这里把主机的 /home/developer/rknn-toolkit2/model_convert 目录挂载到容器的 /test 目录）
docker run -t -i --privileged -v /dev/bus/usb:/dev/bus/usb -v /home/developer/rknn-toolkit2/model_convert:/test rknn-toolkit2:2.3.0-cp38 /bin/bashcd test

就能进入对应的环境内部。

1.2 配置相关

1.2.1 测试代码相关

CLASSES = ("person", "bicycle", "car", "motorbike ", "aeroplane ", "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", "sofa","pottedplant", "bed", "diningtable", "toilet ", "tvmonitor", "laptop	", "mouse	", "remote ", "keyboard ", "cell phone", "microwave ","oven ", "toaster", "sink", "refrigerator ", "book", "clock", "vase", "scissors ", "teddy bear ", "hair drier", "toothbrush ")

要看你进行的测试类别有多少个。

IMG_PATH = './street.jpg'#测试的图片
OBJ_THRESH = 0.25#置信度
NMS_THRESH = 0.45#nms阙值
1.2.2  模型导入路径/rk加载config
ONNX_MODEL = 'yolov5s.onnx'#onnx模型路径（默认在当前文件路径下）
RKNN_MODEL = 'yolov5s_quant.rknn'#导出模型名称
DATASET = './datasets.txt'#用于量化的图片
需要解释的主要是第三个，该txt里面的每一行放置的是每一张图片的相对路径或者绝对路径
QUANTIZE_ON = True#是否开启量化
IMG_SIZE = 640#因为yolov5一般要求推理的图片输入大小是640*640，跟训练一致rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3576')#这三个分别是归一化的均值方差，你最终使用这个模型使用的瑞芯微芯片类型

2.1 生成rk模型

根据上面的步骤已经可以把yolov5s.onnx模型进行转化了。

python （对应的完整代码的完整文件名字）

3.1完整代码展示

import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNNONNX_MODEL = 'yolov5s.onnx'
RKNN_MODEL = 'yolov5s_quant.rknn'
IMG_PATH = './street.jpg'
DATASET = './datasets.txt'QUANTIZE_ON = TrueOBJ_THRESH = 0.25
NMS_THRESH = 0.45
IMG_SIZE = 640CLASSES = ("person", "bicycle", "car", "motorbike ", "aeroplane ", "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", "sofa","pottedplant", "bed", "diningtable", "toilet ", "tvmonitor", "laptop	", "mouse	", "remote ", "keyboard ", "cell phone", "microwave ","oven ", "toaster", "sink", "refrigerator ", "book", "clock", "vase", "scissors ", "teddy bear ", "hair drier", "toothbrush ")def sigmoid(x):return 1 / (1 + np.exp(-x))def xywh2xyxy(x):# Convert [x, y, w, h] to [x1, y1, x2, y2]y = np.copy(x)y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left xy[:, 1] = x[:, 1] - x[:, 3] / 2  # top left yy[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right xy[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right yreturn ydef process(input, mask, anchors):anchors = [anchors[i] for i in mask]grid_h, grid_w = map(int, input.shape[0:2])box_confidence = sigmoid(input[..., 4])box_confidence = np.expand_dims(box_confidence, axis=-1)box_class_probs = sigmoid(input[..., 5:])box_xy = sigmoid(input[..., :2])*2 - 0.5col = np.tile(np.arange(0, grid_w), grid_w).reshape(-1, grid_w)row = np.tile(np.arange(0, grid_h).reshape(-1, 1), grid_h)col = col.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)row = row.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)grid = np.concatenate((col, row), axis=-1)box_xy += gridbox_xy *= int(IMG_SIZE/grid_h)box_wh = pow(sigmoid(input[..., 2:4])*2, 2)box_wh = box_wh * anchorsbox = np.concatenate((box_xy, box_wh), axis=-1)return box, box_confidence, box_class_probsdef filter_boxes(boxes, box_confidences, box_class_probs):"""Filter boxes with box threshold. It's a bit different with origin yolov5 post process!# Argumentsboxes: ndarray, boxes of objects.box_confidences: ndarray, confidences of objects.box_class_probs: ndarray, class_probs of objects.# Returnsboxes: ndarray, filtered boxes.classes: ndarray, classes for boxes.scores: ndarray, scores for boxes."""boxes = boxes.reshape(-1, 4)box_confidences = box_confidences.reshape(-1)box_class_probs = box_class_probs.reshape(-1, box_class_probs.shape[-1])_box_pos = np.where(box_confidences >= OBJ_THRESH)boxes = boxes[_box_pos]box_confidences = box_confidences[_box_pos]box_class_probs = box_class_probs[_box_pos]class_max_score = np.max(box_class_probs, axis=-1)classes = np.argmax(box_class_probs, axis=-1)_class_pos = np.where(class_max_score >= OBJ_THRESH)boxes = boxes[_class_pos]classes = classes[_class_pos]scores = (class_max_score* box_confidences)[_class_pos]return boxes, classes, scoresdef nms_boxes(boxes, scores):"""Suppress non-maximal boxes.# Argumentsboxes: ndarray, boxes of objects.scores: ndarray, scores of objects.# Returnskeep: ndarray, index of effective boxes."""x = boxes[:, 0]y = boxes[:, 1]w = boxes[:, 2] - boxes[:, 0]h = boxes[:, 3] - boxes[:, 1]areas = w * horder = scores.argsort()[::-1]keep = []while order.size > 0:i = order[0]keep.append(i)xx1 = np.maximum(x[i], x[order[1:]])yy1 = np.maximum(y[i], y[order[1:]])xx2 = np.minimum(x[i] + w[i], x[order[1:]] + w[order[1:]])yy2 = np.minimum(y[i] + h[i], y[order[1:]] + h[order[1:]])w1 = np.maximum(0.0, xx2 - xx1 + 0.00001)h1 = np.maximum(0.0, yy2 - yy1 + 0.00001)inter = w1 * h1ovr = inter / (areas[i] + areas[order[1:]] - inter)inds = np.where(ovr <= NMS_THRESH)[0]order = order[inds + 1]keep = np.array(keep)return keepdef yolov5_post_process(input_data):masks = [[0, 1, 2], [3, 4, 5], [6, 7, 8]]anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],[59, 119], [116, 90], [156, 198], [373, 326]]boxes, classes, scores = [], [], []for input, mask in zip(input_data, masks):b, c, s = process(input, mask, anchors)b, c, s = filter_boxes(b, c, s)boxes.append(b)classes.append(c)scores.append(s)boxes = np.concatenate(boxes)boxes = xywh2xyxy(boxes)classes = np.concatenate(classes)scores = np.concatenate(scores)nboxes, nclasses, nscores = [], [], []for c in set(classes):inds = np.where(classes == c)b = boxes[inds]c = classes[inds]s = scores[inds]keep = nms_boxes(b, s)nboxes.append(b[keep])nclasses.append(c[keep])nscores.append(s[keep])if not nclasses and not nscores:return None, None, Noneboxes = np.concatenate(nboxes)classes = np.concatenate(nclasses)scores = np.concatenate(nscores)return boxes, classes, scoresdef draw(image, boxes, scores, classes):"""Draw the boxes on the image.# Argument:image: original image.boxes: ndarray, boxes of objects.classes: ndarray, classes of objects.scores: ndarray, scores of objects.all_classes: all classes name."""for box, score, cl in zip(boxes, scores, classes):top, left, right, bottom = boxprint('class: {}, score: {}'.format(CLASSES[cl], score))print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))top = int(top)left = int(left)right = int(right)bottom = int(bottom)cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),(top, left - 6),cv2.FONT_HERSHEY_SIMPLEX,0.6, (0, 0, 255), 2)def letterbox(im, new_shape=(640, 640), color=(0, 0, 0)):# Resize and pad image while meeting stride-multiple constraintsshape = im.shape[:2]  # current shape [height, width]if isinstance(new_shape, int):new_shape = (new_shape, new_shape)# Scale ratio (new / old)r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])# Compute paddingratio = r, r  # width, height ratiosnew_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh paddingdw /= 2  # divide padding into 2 sidesdh /= 2if shape[::-1] != new_unpad:  # resizeim = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))left, right = int(round(dw - 0.1)), int(round(dw + 0.1))im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add borderreturn im, ratio, (dw, dh)if __name__ == '__main__':# Create RKNN objectrknn = RKNN(verbose=True)# pre-process configprint('--> Config model')rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3576')print('done')# Load ONNX modelprint('--> Loading model')ret = rknn.load_onnx(model=ONNX_MODEL)if ret != 0:print('Load model failed!')exit(ret)print('done')# Build modelprint('--> Building model')ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET)if ret != 0:print('Build model failed!')exit(ret)print('done')# Export RKNN modelprint('--> Export rknn model')ret = rknn.export_rknn(RKNN_MODEL)if ret != 0:print('Export rknn model failed!')exit(ret)print('done')# Init runtime environmentprint('--> Init runtime environment')ret = rknn.init_runtime()# ret = rknn.init_runtime('rk3566')if ret != 0:print('Init runtime environment failed!')exit(ret)print('done')# Set inputsimg = cv2.imread(IMG_PATH)# img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))# Inferenceprint('--> Running model')outputs = rknn.inference(inputs=[img])np.save('./onnx_yolov5_0.npy', outputs[0])np.save('./onnx_yolov5_1.npy', outputs[1])np.save('./onnx_yolov5_2.npy', outputs[2])print('done')# post processinput0_data = outputs[0]input1_data = outputs[1]input2_data = outputs[2]input0_data = input0_data.reshape([3, -1]+list(input0_data.shape[-2:]))input1_data = input1_data.reshape([3, -1]+list(input1_data.shape[-2:]))input2_data = input2_data.reshape([3, -1]+list(input2_data.shape[-2:]))input_data = list()input_data.append(np.transpose(input0_data, (2, 3, 0, 1)))input_data.append(np.transpose(input1_data, (2, 3, 0, 1)))input_data.append(np.transpose(input2_data, (2, 3, 0, 1)))boxes, classes, scores = yolov5_post_process(input_data)img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)if boxes is not None:draw(img_1, boxes, scores, classes)cv2.imwrite('result.png', img_1)rknn.release()

（代码详解后续发布）

http://www.xdnf.cn/news/1328851.html

相关文章：

  • 玳瑁的嵌入式日记D20-08019（数据结构）
  • 安装DDNS-go
  • Linux操作系统编程——进程间的通信
  • RocketMq消费者动态订阅topic
  • RK3568 Linux驱动学习——Linux设备树
  • Linux下Mysql命令，创建mysql，删除mysql
  • Win/Linux笔记本合盖不睡眠设置指南
  • 小程序插件使用
  • RWA加密金融高峰论坛星链品牌全球发布 —— 稳定币与Web3的香港新篇章
  • Vue 2 项目中快速集成 Jest 单元测试（超详细教程）
  • 哈希：两数之和
  • 从零开始的云计算生活——第四十六天，铁杵成针，kubernetes模块之Configmap资源与Secret资源对象
  • 【技术揭秘】AI Agent操作系统架构演进：从单体到分布式智能的跃迁
  • 告别手写文档！Spring Boot API 文档终极解决方案：SpringDoc OpenAPI
  • 大数据数据库 —— 初见loTDB
  • 视觉采集模块的用法
  • A股大盘数据-20250819 分析
  • 云原生俱乐部-shell知识点归纳（1）
  • 力扣57:插入区间
  • 决策树剪枝及数据处理
  • AI 药物发现：化学分子到机器学习数值特征的转化——打通“化学空间”与“模型空间”关键路径
  • 【Git 子模块与动态路由映射技术分析文档】
  • Matplotlib数据可视化实战：Matplotlib子图布局与管理入门
  • 疏老师-python训练营-Day50预训练模型+CBAM注意力
  • PCL+Spigot服务器+python进行MC编程（使用Trae进行AI编程）---可以生成彩虹
  • Hugging Face 核心组件介绍
  • 35岁对工作的一些感悟
  • Ansible 中的文件包含与导入机制
  • noetic版本/ubuntu20 通过moveit控制真实机械臂
  • 常见的对比学习的损失函数