首页 » 机器视觉 » 正文
机器视觉

将yolo-fastest自训练模型转成rknn，并在rv1126下实现推理

关于如何用训练自己的yolo-fastest模型，上一篇博文已经说明，现记录先近期的实验。

环境：
系统：ubuntu1804
软件：rknn-toolkit 1.6.0（根据Rockchip_Quick_Start_RKNN_Toolkit_Vx.x.x_CN.pdf文档，部署好其他软件环境，opencv numpy tensorflow…等一系列依赖）
硬件：rv1126开发板（rp pro-rv1126 2+8）

一、模型转换
1、将准备好相应的文件
（1）yolo-fastest.cfg，该文件是自己训练时候修改过的配置文件
（2）yolo-fastest_best.weights， 自训练的权重文件
（3）ai_0006.jpg，需要推理的图片
（4）dataset.txt，该文件的内容是推理图片的路径，如下

./ai_0006.jpg

（5）trans-yolofastest.py，内容如下

from PIL import Image
import numpy as np
from matplotlib import pyplot as plt
import re
import math
import random
from rknn.api import RKNN

if __name__ == '__main__':
	rknn=RKNN()
	print('load model...')
	ret = rknn.load_darknet(model='./yolo-fastest.cfg', weight='./yolo-fastest_best.weights')
	if ret != 0:
		print('load err...')
		exit(ret)
	print('done')
	
	rknn.config(reorder_channel='0,1,2', mean_values=[[0,0,0]],std_values=[[255,255,255]],target_platform=['rv1126'])
	
	print('building...')
	ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
	if ret != 0:
		print('build fail!')
		exit(ret)
	print('done')
	
	ret = rknn.export_rknn('./yolo-fastest.rknn')
	if ret != 0:
		print('export fail!')
		exit(ret)
	exit(0)

2、对模型进行转换
（1）确保已经在文章开头描述的软件环境中
（2）运行模型转换代码

yolo-fast-zyj$ python3 trans-yolofastest.py

运行结果如下图，并查看路径下是否已经生成rknn模型
在这里插入图片描述
二、模型推理
1、准备好推理代码文件run_yolo-fastest_rknn.py，需要修改几个关键的地方
（1）GRID0、GRID1根据yolo算法的grid cell来修改；就是输出单元大小，例如yolov3是13x13,26x26,52x52。
（2）LISTSIZE=NUL_CLS+5，就是识别种类加5，比如yolov4识别80种类，则LISTSIZE=80+5，我这里只识别两个种类，所以填的LISTSIZE=7
（3）CLASSES为识别种类，也就是标注的时候填的类别名称
（4）masks和anchors根据yolo-fastest.cfg文件来填写
（5）配置目标NPU和ID，rknn.init_runtime(target=‘rv1126’,device_id=‘6de927292515e514’)
（6）图像处理outputs在处理时要注意输出的维度，有时候reshape会报异常是因为你前面的GRID0~2配置不对。
具体修改后的代码如下

from PIL import Image
import numpy as np
from matplotlib import pyplot as plt

import re
import math
import random
import cv2

from rknn.api import RKNN

GRID0 = 10
GRID1 = 20
GRID2 = 52
LISTSIZE = 7
SPAN = 3
NUM_CLS = 2
MAX_BOXES = 500
OBJ_THRESH = 0.5
NMS_THRESH = 0.6

'''
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 ")

CLASSES = ("aeroplane","bicycle","bird","boat","bottle","bus","car","cat","chair","cow","diningtable","dog","horse","motorbike","person","pottedplant",
"sheep","sofa","train","tvmonitor")
'''
CLASSES = ("zyj","muzhuang")

def sigmoid(x):
    return 1 / (1 + np.exp(-x))


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])
    box_wh = np.exp(input[..., 2:4])
    box_wh = box_wh * anchors

    col = 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 += grid
    box_xy /= (grid_w, grid_h)
    box_wh /= (416, 416)
    box_xy -= (box_wh / 2.)
    box = np.concatenate((box_xy, box_wh), axis=-1)

    return box, box_confidence, box_class_probs

def filter_boxes(boxes, box_confidences, box_class_probs):
    """Filter boxes with object threshold.

    # Arguments
        boxes: ndarray, boxes of objects.
        box_confidences: ndarray, confidences of objects.
        box_class_probs: ndarray, class_probs of objects.

    # Returns
        boxes: ndarray, filtered boxes.
        classes: ndarray, classes for boxes.
        scores: ndarray, scores for boxes.
    """
    box_scores = box_confidences * box_class_probs
    box_classes = np.argmax(box_scores, axis=-1)
    box_class_scores = np.max(box_scores, axis=-1)
    pos = np.where(box_class_scores >= OBJ_THRESH)

    boxes = boxes[pos]
    classes = box_classes[pos]
    scores = box_class_scores[pos]

    return boxes, classes, scores

def nms_boxes(boxes, scores):
    """Suppress non-maximal boxes.

    # Arguments
        boxes: ndarray, boxes of objects.
        scores: ndarray, scores of objects.

    # Returns
        keep: ndarray, index of effective boxes.
    """
    x = boxes[:, 0]
    y = boxes[:, 1]
    w = boxes[:, 2]
    h = boxes[:, 3]

    areas = w * h
    order = 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 * h1

        ovr = inter / (areas[i] + areas[order[1:]] - inter)
        inds = np.where(ovr <= NMS_THRESH)[0]
        order = order[inds + 1]
    keep = np.array(keep)
    return keep


def yolov4_post_process(input_data):
    # yolov3
    # masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
    # anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
    #          [59, 119], [116, 90], [156, 198], [373, 326]]
    # yolov3-tiny
    # masks = [[3, 4, 5], [0, 1, 2]]
    # anchors = [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]]

    #yolov4
    #masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
    #anchors = [[12, 16], [19, 36], [40, 28], [36, 75], [76, 55], [72, 146], [142, 110], [192, 243], [459, 401]]
    
    #yolov4-tiny
    #masks = [[1, 2, 3], [3, 4, 5]]
    #anchors = [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]]

    #yolo-fastest
    masks = [[0, 1, 2], [3, 4, 5]]
    anchors = [[26, 48], [67, 84], [72, 175], [189, 126], [137, 236], [265, 259]]

    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)
    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, None

    boxes = np.concatenate(nboxes)
    classes = np.concatenate(nclasses)
    scores = np.concatenate(nscores)

    return boxes, classes, scores


def 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):
        x, y, w, h = box
        print('class: {}, score: {}'.format(CLASSES[cl], score))
        print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(x, y, x+w, y+h))
        x *= image.shape[1]
        y *= image.shape[0]
        w *= image.shape[1]
        h *= image.shape[0]
        top = max(0, np.floor(x + 0.5).astype(int))
        left = max(0, np.floor(y + 0.5).astype(int))
        right = min(image.shape[1], np.floor(x + w + 0.5).astype(int))
        bottom = min(image.shape[0], np.floor(y + h + 0.5).astype(int))

        # print('class: {}, score: {}'.format(CLASSES[cl], score))
        # print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, 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)

if __name__ == '__main__':

    # Create RKNN object
    rknn = RKNN()

    # Load tensorflow model
    print('--> Loading model')
    ret = rknn.load_rknn('./yolo-fastest.rknn')

    if ret != 0:
        print('load rknn model failed')
        exit(ret)
    print('done')

    # Set inputs
    im_file = 'ai_0006.jpg'
    img = cv2.imread(im_file)
    orig_img = cv2.resize(img, (320,320))
    img = cv2.cvtColor(orig_img, cv2.COLOR_BGR2RGB)

    # init runtime environment
    print('--> Init runtime environment')
    ret = rknn.init_runtime(target='rv1126',device_id='6de927292515e514')
    if ret != 0:
        print('Init runtime environment failed')
        exit(ret)
    print('done')

    # Inference
    print('--> Running model')
    outputs = rknn.inference(inputs=[img])
    
    rknn.release()
    
    #input0_data = np.reshape(outputs[2], (SPAN, LISTSIZE, GRID0, GRID0))
    input1_data = np.reshape(outputs[1], (SPAN, LISTSIZE, GRID1, GRID1))
    input2_data = np.reshape(outputs[0], (SPAN, LISTSIZE, GRID0, GRID0))

    input_data = []
    #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 = yolov4_post_process(input_data)

    if boxes is not None:
        draw(orig_img, boxes, scores, classes)

    cv2.imshow("results",orig_img)
    cv2.waitKeyEx(0)
    print('done')
    exit(0)

2、运行代码及结果如下：

yolo-fast-zyj$ pyhton3 run_yolo-fastest_rknn.py

在这里插入图片描述
三、总结
倒腾了好几次，最后终于搞好了。最主要还是要到官方去找下资料，细心点就OK了。

版权声明：本文为CSDN博主「weixin_30072103」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_30072103/article/details/117510493

标签： · · · ·
点赞 0

weixin_30072103

我还没有学会写个人说明！

暂无评论

发表评论

相关推荐

yolov5训练的小技巧
机器视觉 2023-08-15

yolov5训练的小技巧

从数据集上 每个类别的图片数：推荐每个类别的图片数>1500每个类别的实例数：每个类的实例（标记对象）>10000图片多样性：必须使用已部署的环境为代表。对于真实用例&#x

分享到：