瑞芯微RV1126/1109开发流程之模型转换

1、环境搭建（PC端ubuntu16.04搭建rknn环境）

（1）安装anaconda环境（为了便于管理自己的环境建议安装，安装步骤请自行搜索，本人安装anaconda版本为Anaconda3-2019-Linux-x86_64.sh）

（2）下载rknn安装包

关于版本问题：建议安装瑞芯微更新的最新版本，本人之前用1.6在模型转换过程中出现莫名错误。

下载链接https://github.com/rockchip-linux/rknn-toolkit

本人安装（版本1.7.1）链接：

1）源码链接https://pan.baidu.com/s/1r7zg8MPWIKagUkAguYTyhA 提取码：ajbk

说明：红色框是需要安装的rknn的sdk开发环境，绿色框为瑞芯微官方提供的开发source源码

（3）安装rknn环境

1）创建虚拟环境

conda create -n rk_env_1.7 python=3.6

2）安装依赖

pip install tensorflow-gpu==1.14.0pip install torch==1.5.1pip install torchvision==0.4.0pip install mxnet-cu101==1.5.0pip3 install opencv-pythonpip3 install gluoncv

3）安装rknn包

pip install rknn_toolkit-1.7.1-cp36-cp36m-linux_x86_64.whl

4）测试是否安装成功

2、模型转换

（1）yolov5s.pt转yolov5.onnx

Yolov5版本一直再不停的更换，瑞芯微使用的是yolov5 5.0版本

工程源码以及下载链接：https://github.com/ultralytics/yolov5/releases

ps:转换成onnx过程中修改yolo.py，修改如下：

（2）转换成onnx命令

 export PYTHONPATH="$PWD" && python models/export.py --weights ./weights/yolov5s.pt --img 640 --batch 1

（3）onnx转换从成rknn

命令：

python yolov5_rknn.py

源码：

import os
import sys
import numpy as np
from rknn.api import RKNNONNX_MODEL = 'yolov5s.onnx'
RKNN_MODEL = 'yolov5s.rknn'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]], reorder_channel='0 1 2', target_platform='rv1126',quantized_dtype='asymmetric_affine-u8', optimization_level=3,   output_optimize=1)print('done')print('--> 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=True, dataset='./dataset.txt')#,pre_compile=Trueif ret != 0:print('Build yolov5s failed!')exit(ret)print('done')# Export rknn modelprint('--> Export RKNN model')ret = rknn.export_rknn(RKNN_MODEL)if ret != 0:print('Export yolov5s.rknn failed!')exit(ret)print('done')rknn.release()

3、可视化推理测试rknn模型

import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNNRKNN_MODEL = 'yolov5s.rknn'
IMG_PATH = 'dog.jpg'QUANTIZE_ON = TrueBOX_THRESH = 0.5
NMS_THRESH = 0.6
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 y
def resize_postprocess(x, offset_x, offset_y):# Convert [x1, y1, x2, y2] to [x1, y1, x2, y2]y = np.copy(x)y[:, 0] = x[:, 0]  / offset_x  # top left xy[:, 1] = x[:, 1]  / offset_y  # top left yy[:, 2] = x[:, 2]  / offset_x  # bottom right xy[:, 3] = x[:, 3]  / offset_y  # bottom right yreturn y
def 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."""box_classes = np.argmax(box_class_probs, axis=-1)box_class_scores = np.max(box_class_probs, axis=-1)pos = np.where(box_confidences[...,0] >= BOX_THRESH)boxes = boxes[pos]classes = box_classes[pos]scores = box_class_scores[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)
def letter_box_postprocess(x, scalingfactor, xy_correction):y = np.copy(x)y[:, 0] = (x[:, 0]-xy_correction[0])  / scalingfactor  # top left xy[:, 1] = (x[:, 1]-xy_correction[1])  / scalingfactor  # top left yy[:, 2] = (x[:, 2]-xy_correction[0])  / scalingfactor  # bottom right xy[:, 3] = (x[:, 3]-xy_correction[1])  / scalingfactor  # bottom right yreturn y
def get_file(filepath):templist = []with open(filepath, "r") as f:for item in f.readlines():templist.append(item.strip())return templist
if __name__ == '__main__':# Create RKNN objectrknn = RKNN()image_process_mode = "letter_box"print("image_process_mode = ", image_process_mode)if not os.path.exists(RKNN_MODEL):print('model not exist')exit(-1)# Load ONNX modelprint('--> Loading model')ret = rknn.load_rknn(RKNN_MODEL)if ret != 0:print('Load rknn model failed!')exit(ret)print('done')# init runtime environmentprint('--> Init runtime environment')ret = rknn.init_runtime()# ret = rknn.init_runtime('rk180_8', device_id='1808')if ret != 0:print('Init runtime environment failed')exit(ret)print('done')image_list = get_file("test_image.txt")for image_path in image_list:# Set inputsimage = cv2.imread(image_path)image_name = image_path.split("/")[-1]img_height = image.shape[0]img_width = image.shape[1]# img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)if image_process_mode == "resize":img = cv2.resize(img,(IMG_SIZE, IMG_SIZE))elif image_process_mode == "letter_box":img, scale_factor, correction = letterbox(img)# Inferenceprint('--> Running model')outputs = rknn.inference(inputs=[img])# 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)if image_process_mode == "resize":scale_h = IMG_SIZE / img_heightscale_w = IMG_SIZE / img_widthboxes = resize_postprocess(boxes, scale_w, scale_h)elif image_process_mode == "letter_box":boxes = letter_box_postprocess(boxes, scale_factor[0], correction)# img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)if boxes is not None:draw(image, boxes, scores, classes)cv2.imwrite("./" + image_name, image)rknn.release()

ps：本人对瑞芯微给的rknn测试demo程序做了修改-官方demo只给出了对图片resize的预处理方式且后处理并未还原到原始图片尺寸的大小；本人已经加入了resize和letterbox方式且不同的预处理会有不同的后处理方式

可视化测试结果：

瑞芯微RV1126/1109开发流程之模型转换相关推荐

瑞芯微RV1126/1109开发流程之驱动升级
1.1126硬件参数读取 (1)CPU温度读取 46300和47100分别代表46.3.47.1 (2)查看1126的NPU (3)查询NPU驱动版本 dmesg | grep -i galcore ...
瑞芯微RV1126 BuildRoot开发学习笔记
1.BuildRoot如何增加一个包? 参考 < The Buildroot User Manual.pdf >第17章 2.BuildRoot如何单独编译某一个包? 如果修改了源码,在编 ...
yolov5-5.0训练模型+瑞芯微rv1126上实现模型部署
yolov5-5.0训练模型+瑞芯微rv1126上实现模型部署第一次接触模型训练和在开发板部署,过程曲折,从开始的一脸懵到最后模型部署成功,查阅了不少资料和学习了不少大佬的经验,在这里记录一下过 ...
瑞芯微RK3399嵌入式开发板Wifi 驱动 build in 方式
RK3399的CPU采用big.LITTLE大小核架构,双Cortex-A72大核+四Cortex-A53小核结构,对整数.浮点.内存等作了大幅优化,在整体性能.功耗及核心面积三个方面都具革命性提升 ...
瑞芯微RK3399芯片开发板香橙派4的HDMI音频播放功能测试（Linux系统）
瑞芯微RK3399芯片开发板香橙派OrangePi 4(16G)用拥有4G内存16G存储,集成双频WiFi.蓝牙5.0.HDMI输出.千兆网口.USB接口等丰富的功能接口,支持双摄像头输入和两路视频输 ...
[基于瑞芯微RV1126调试RTL8818FU WIFI模组支持STA和AP模式]
基于瑞芯微RV1126调试RTL8818FU WIFI模组支持STA和AP模式内核menuconfig配置内核dts配置文件系统配置和更改驱动编译 wifi工具编译 libnl库编译 open ...
瑞芯微rv1126 rtsp+mpp+rga取流
提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档瑞芯微rv1126 rtsp+mpp+rga取流一.mpp解码二.rga转换经过测试,使用rtsp+mpp+rga取流1920* ...
瑞芯微rv1126+yolov3模型转换
瑞芯微rv1126+yolov3模型转换文章目录瑞芯微rv1126+yolov3模型转换环境准备一.加载运行docker 1.安装 Docker 2. 加载镜像二.转换步骤 1.下载yolo ...
瑞芯微RV1126平台----yolov5输出后处理C++实现
目录 1.前言 2.代码 2.1 padding resize 代码 2.2 瑞芯微yolov5后处理 2.3 坐标框的后处理 3.完整代码

瑞芯微RV1126/1109开发流程之模型转换

瑞芯微RV1126/1109开发流程之模型转换相关推荐

最新文章

热门文章