MENU

Yolo Anchor数值 聚类分析

December 24, 2020 • 学习

用于产生 Anchor 值的聚类分析代码,参考于:kmeans-anchor-boxes

仅供归档

# -*- coding=utf-8 -*-
# file name: calcAnchor.py
import glob
import os
import sys
import xml.etree.ElementTree as ET
import numpy as np
from kmeans import kmeans, avg_iou

# 根文件夹,VOC-XML类型的数据集
ROOT_PATH = '/data/DataBase/YOLO_Data/V3_DATA/'
# 聚类的数目
CLUSTERS = 6
# 模型中图像的输入尺寸,默认是一样的
# 用于K210平台上的一般为224(必须为32的整倍数)
SIZE = 224

# 加载YOLO格式的标注数据
def load_dataset(path):
    jpegimages = os.path.join(path, 'JPEGImages')
    if not os.path.exists(jpegimages):
        print('no JPEGImages folders, program abort')
        sys.exit(0)
    labels_txt = os.path.join(path, 'labels')
    if not os.path.exists(labels_txt):
        print('no labels folders, program abort')
        sys.exit(0)

    label_file = os.listdir(labels_txt)
    print('label count: {}'.format(len(label_file)))
    dataset = []

    for label in label_file:
        with open(os.path.join(labels_txt, label), 'r') as f:
            txt_content = f.readlines()

        for line in txt_content:
            line_split = line.split(' ')
            roi_with = float(line_split[len(line_split)-2])
            roi_height = float(line_split[len(line_split)-1])
            if roi_with == 0 or roi_height == 0:
                continue
            dataset.append([roi_with, roi_height])
            # print([roi_with, roi_height])

    return np.array(dataset)

data = load_dataset(ROOT_PATH)
out = kmeans(data, k=CLUSTERS)

print(out)
print("Accuracy: {:.2f}%".format(avg_iou(data, out) * 100))
print("Boxes:\n {}-{}".format(out[:, 0] * SIZE, out[:, 1] * SIZE))

ratios = np.around(out[:, 0] / out[:, 1], decimals=2).tolist()
print("Ratios:\n {}".format(sorted(ratios)))

label count: 344
[[0.09090909 0.11363636]
[0.10795455 0.1504329 ]
[0.13230519 0.17532468]
[0.21753247 0.22943723]
[0.35064935 0.45238095]
[0.6875 0.66287879]]
Accuracy: 81.42%
Boxes:
[ 20.36363636 24.18181818 29.63636364 48.72727273 78.54545455 154. ]

-[ 25.45454545 33.6969697 39.27272727 51.39393939 101.33333333 148.48484848]

Ratios: [0.72, 0.75, 0.78, 0.8, 0.95, 1.04]

可得出 Anchor 参数:[20, 25, 24, 33, 29, 39, 48, 51, 78, 101, 154, 148]

# file name: kmeans.py
import numpy as np


def iou(box, clusters):
    """
    Calculates the Intersection over Union (IoU) between a box and k clusters.
    :param box: tuple or array, shifted to the origin (i. e. width and height)
    :param clusters: numpy array of shape (k, 2) where k is the number of clusters
    :return: numpy array of shape (k, 0) where k is the number of clusters
    """
    x = np.minimum(clusters[:, 0], box[0])
    y = np.minimum(clusters[:, 1], box[1])
    if np.count_nonzero(x == 0) > 0 or np.count_nonzero(y == 0) > 0:
        raise ValueError("Box has no area")

    intersection = x * y
    box_area = box[0] * box[1]
    cluster_area = clusters[:, 0] * clusters[:, 1]

    iou_ = intersection / (box_area + cluster_area - intersection)

    return iou_


def avg_iou(boxes, clusters):
    """
    Calculates the average Intersection over Union (IoU) between a numpy array of boxes and k clusters.
    :param boxes: numpy array of shape (r, 2), where r is the number of rows
    :param clusters: numpy array of shape (k, 2) where k is the number of clusters
    :return: average IoU as a single float
    """
    return np.mean([np.max(iou(boxes[i], clusters)) for i in range(boxes.shape[0])])


def translate_boxes(boxes):
    """
    Translates all the boxes to the origin.
    :param boxes: numpy array of shape (r, 4)
    :return: numpy array of shape (r, 2)
    """
    new_boxes = boxes.copy()
    for row in range(new_boxes.shape[0]):
        new_boxes[row][2] = np.abs(new_boxes[row][2] - new_boxes[row][0])
        new_boxes[row][3] = np.abs(new_boxes[row][3] - new_boxes[row][1])
    return np.delete(new_boxes, [0, 1], axis=1)

def kmeans(boxes, k, dist=np.median):
    """
    Calculates k-means clustering with the Intersection over Union (IoU) metric.
    :param boxes: numpy array of shape (r, 2), where r is the number of rows
    :param k: number of clusters
    :param dist: distance function
    :return: numpy array of shape (k, 2)
    """
    rows = boxes.shape[0]

    distances = np.empty((rows, k))
    last_clusters = np.zeros((rows,))

    np.random.seed()

    # the Forgy method will fail if the whole array contains the same rows
    clusters = boxes[np.random.choice(rows, k, replace=False)]

    while True:
        for row in range(rows):
            distances[row] = 1 - iou(boxes[row], clusters)

        nearest_clusters = np.argmin(distances, axis=1)

        if (last_clusters == nearest_clusters).all():
            break

        for cluster in range(k):
            clusters[cluster] = dist(boxes[nearest_clusters == cluster], axis=0)

        last_clusters = nearest_clusters

    return clusters

即日起关闭全站评论区,您可以通过关于页面的电邮地址和我取得联系,谢谢

Last Modified: January 28, 2021
Archives QR Code
QR Code for this page
Tipping QR Code