YOLO-V3代码解析系列（三） —— 数据处理（dataset.py）
代码结构
Dataset类代码结构：
- 初始化数据类，设置训练相关参数
parse_annotation()：将图像和标签处理到特定尺度，以及相应的预处理preprocess_true_boxes()：进一步处理标签数据，具体见代码和注释
代码解析
import os
import cv2
import random
import numpy as np
import tensorflow as tf
import core.utils as utils
from core.config import cfg
class Dataset(object):
"""implement Dataset here"""
def __init__(self, dataset_type):
self.annot_path = cfg.TRAIN.ANNOT_PATH if dataset_type == 'train' else cfg.TEST.ANNOT_PATH
self.input_sizes = cfg.TRAIN.INPUT_SIZE if dataset_type == 'train' else cfg.TEST.INPUT_SIZE
self.batch_size = cfg.TRAIN.BATCH_SIZE if dataset_type == 'train' else cfg.TEST.BATCH_SIZE
self.data_aug = cfg.TRAIN.DATA_AUG if dataset_type == 'train' else cfg.TEST.DATA_AUG
# 多尺度训练：训练过程中，随机选择预先设定的输入尺度，必须为32的整倍数
# [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
self.train_input_sizes = cfg.TRAIN.INPUT_SIZE
# 网络输出尺度，yolov3总共三个尺度，output_stride=[8, 16, 32]
# 分别针对小、中、大目标
self.strides = np.array(cfg.YOLO.STRIDES)
self.classes = utils.read_class_names(cfg.YOLO.CLASSES)
self.num_classes = len(self.classes)
# 加载提前生成的anchor数据
self.anchors = np.array(utils.get_anchors(cfg.YOLO.ANCHORS))
self.anchor_per_scale = cfg.YOLO.ANCHOR_PER_SCALE
self.max_bbox_per_scale = 150
# 加载训练文本的全部数据
self.annotations = self.load_annotations()
self.num_samples = len(self.annotations)
self.num_batchs = int(np.ceil(self.num_samples / self.batch_size))
self.batch_count = 0
def load_annotations(self):
# 训练集路径以及目标框标注, 读取制作的train.txt
# train.txt中每一条数据内容：image_path+image_name xmin,ymin,xmax,ymax,class_id
with open(self.annot_path, 'r') as f:
txt = f.readlines()
annotations = [line.strip() for line in txt if len(line.strip().split()[1:]) != 0]
np.random.shuffle(annotations)
return annotations
# 表明该数据类是可迭代类
def __iter__(self):
return self
# 可迭代对象具体的迭代算法
def __next__(self):
# 循环读取数据集
with tf.device('/cpu:0'):
# 多尺度训练, 随机选出一个尺度训练
self.train_input_size = random.choice(self.train_input_sizes)
# 网络输出, output_stride: [8, 16, 32]
self.train_output_sizes = self.train_input_size // self.strides
# 存储输入图像一个batch数据的numpy数组容器
batch_image = np.zeros((self.batch_size, self.train_input_size, self.train_input_size, 3))
# 存储不同输出尺度下一个batch标签的数据
batch_label_sbbox = np.zeros((self.batch_size,
self.train_output_sizes[0],
self.train_output_sizes[0],
self.anchor_per_scale,
5 + self.num_classes))
batch_label_mbbox = np.zeros((self.batch_size,
self.train_output_sizes[1],
self.train_output_sizes[1],
self.anchor_per_scale,
5 + self.num_classes))
batch_label_lbbox = np.zeros((self.batch_size,
self.train_output_sizes[2],
self.train_output_sizes[2],
self.anchor_per_scale,
5 + self.num_classes))
# 输出真实框的数据
batch_sbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
batch_mbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
batch_lbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4))
# 读取数据,实际上每次只度一个batch,然后填入网络训练. GPU大部分时间处于闲置
# 状态. 所以,训练速度很慢,TitanXp上测试相差30倍.
num = 0
if self.batch_count < self.num_batchs:
# print('if if if')
while num < self.batch_size:
index = self.batch_count * self.batch_size + num
if index >= self.num_samples:
index -= self.num_samples
# 读取一条数据
annotation = self.annotations[index]
# 图像和目标框处理为目标尺度上的数值，比如随机选择一个尺度
# [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
image, bboxes = self.parse_annotation(annotation)
# 进一步处理真实标签：用于后续损失函数计算，处理流程如下，
# 1. 标签平滑(one-hot)
# 2. 边框坐标(xmin,ymin,xmax,ymax)转为(x,y,w,h)
# 3. 存储每个尺度下的label和bboxes.
# label:每种尺度下，大于iou阈值，则填充真实标签
# shape:(3,output_size,output_size,anchor_per_scale,5+num_class)
# bboxes:大于iou(0.3),则填充真实框的中心坐标和宽高,shape:(3, 150, 4)
label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.preprocess_true_boxes(bboxes)
batch_image[num, :, :, :] = image
batch_label_sbbox[num, :, :, :, :] = label_sbbox
batch_label_mbbox[num, :, :, :, :] = label_mbbox
batch_label_lbbox[num, :, :, :, :] = label_lbbox
# print('batch: ', batch_label_sbbox.shape)
batch_sbboxes[num, :, :] = sbboxes
batch_mbboxes[num, :, :] = mbboxes
batch_lbboxes[num, :, :] = lbboxes
num += 1
self.batch_count += 1
return batch_image, \
batch_label_sbbox, \
batch_label_mbbox, \
batch_label_lbbox, \
batch_sbboxes, \
batch_mbboxes, \
batch_lbboxes
else:
# print('else else else')
self.batch_count = 0
np.random.shuffle(self.annotations)
raise StopIteration
image, bboxes = self.parse_annotation(annotation)，该函数主要是将原始尺度下的图像和标签(边界框)处理到目标尺度下，并且进行数据增强操作，增强数据的多样性，进而提升网络的泛化能力。
def parse_annotation(self, annotation):
# 读取图片和标签
line = annotation.split()
image_path = line[0]
if not os.path.exists(image_path):
raise KeyError("%s does not exist ... " % image_path)
image = np.array(cv2.imread(image_path))
bboxes = np.array([list(map(lambda x: int(float(x)), box.split(','))) for box in line[1:]])
# 数据增强处理
if self.data_aug:
image, bboxes = self.random_horizontal_flip(np.copy(image), np.copy(bboxes))
image, bboxes = self.random_crop(np.copy(image), np.copy(bboxes))
image, bboxes = self.random_translate(np.copy(image), np.copy(bboxes))
# 颜色转换(BGR->RGB), 将图片和标签处理到随机选择的尺度,并且填充为正方形
image, bboxes = utils.image_preporcess(np.copy(image),
[self.train_input_size, self.train_input_size],
np.copy(bboxes))
return image, bboxes
label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.preprocess_true_boxes(bboxes)：顾名思义，是对真实框进行进一步预处理，便于后续计算损失函数。为了更好地理解这个函数，有必要先说明bboxes和label分别表示什么，具体怎么操作。
bboxes是用来存放真实框的中心坐标以及宽高(x,y,w,h),其shape为(3,150,4)，3表示3种网格尺寸，150表示每种网格尺寸允许存放的最大真实框数量，4就是(x,y,w,h)。
label是用来存放3种网格尺寸下每一个网格的中心坐标、宽高、置信度以及所属类别，(x, y, w, h, conf, classid)。shape为(3, train_output_sizes, train_output_sizes, anchor_per_scale, 5+num_classes)。label的初始化为0矩阵，即每个网格的信息(x, y, w, h, conf, classid)都填充为0。每个尺度下，分别计算3个先验框和相应尺度下真实框的iou值，筛选iou值>0.3的先验框并标记索引，然后将真实框的(x, y, w, h, class_id)填充到真实框所属的网格中(对应标记索引)，网格的置信度设为1.
def preprocess_true_boxes(self, bboxes):
label = [np.zeros((self.train_output_sizes[i],
self.train_output_sizes[i],
self.anchor_per_scale,
5 + self.num_classes)) for i in range(3)]
# print(label[0].shape)
# print(label[1].shape)
# print(label[2].shape)
# [(150, 4), (150, 4), (150, 4)], 每种stride下最多产生150个真实框
bboxes_xywh = [np.zeros((self.max_bbox_per_scale, 4)) for _ in range(3)]
bbox_count = np.zeros((3,))
for bbox in bboxes:
# 获取坐标和类别值
bbox_coor = bbox[:4]
bbox_class_ind = bbox[4]
# 标签平滑处理
onehot = np.zeros(self.num_classes, dtype=np.float)
onehot[bbox_class_ind] = 1.0
uniform_distribution = np.full(self.num_classes, 1.0 / self.num_classes)
deta = 0.01
smooth_onehot = onehot * (1 - deta) + deta * uniform_distribution
# 计算中心点坐标(x,y) = ((x_max, y_max) + (x_min, y_min)) * 0.5
# 计算宽高(w,h) = (x_max, y_max) - (x_min, y_min), 拼接成一个数组(x, y, w, h).
bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5, bbox_coor[2:] - bbox_coor[:2]], axis=-1)
print('bbox_xywh: ', bbox_xywh)
# bbox_xywh: [431.5 282.5 135. 153. ]
# 8, 16, 32倍对中心点以及宽高缩放, shape=(3, 4)
bbox_xywh_scaled = 1.0 * bbox_xywh[np.newaxis, :] / self.strides[:, np.newaxis]
print(self.strides[:, np.newaxis])
print('bbox_xywh_scaled:\n', bbox_xywh_scaled)
# self.strides[:, np.newaxis] 输出如下：
# [[ 8]
# [16]
# [32]]
# ==========================================
# bbox_xywh_scaled:[x y w h]
# [[53.9375 35.3125 16.875 19.125 ]
# [26.96875 17.65625 8.4375 9.5625 ]
# [13.484375 8.828125 4.21875 4.78125 ]]
iou = []
exist_positive = False
for i in range(3): # 3种stride尺度[8,16,32]
# 用于存储每种网格尺寸[8,16,32]下3个anchor框的中心位置和宽高
anchors_xywh = np.zeros((self.anchor_per_scale, 4))
# 将3种尺度下的anchor分别移到三种尺度下真实框的中心,重合方便计算IOU
# anchor只有宽高,没有中心
anchors_xywh[:, 0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5
anchors_xywh[:, 2:4] = self.anchors[i]
print("anchor[i]:\n", self.anchors[i])
print("anchor_xywh:\n", anchors_xywh)
# anchor[0]: stride=8下的anchor,每个stride下有三个先验anchor
# [[ 16.75 19. ]
# [ 38.75 42.125]
# [ 95.625 110.125]]
# anchor_xywh: 移至到真实框的中心
# [[ 53.5 35.5 16.75 19. ]
# [ 53.5 35.5 38.75 42.125]
# [ 53.5 35.5 95.625 110.125]]
# 计算1个尺度下真实框分别与3个anchor的iou值
iou_scale = self.bbox_iou(bbox_xywh_scaled[i][np.newaxis, :], anchors_xywh)
iou.append(iou_scale)
iou_mask = iou_scale > 0.3
print('iou_mask: ', iou_mask)
# iou_mask = [True,True,False]
# iou > 0.3 的anchor, 执行此处处理
if np.any(iou_mask):
# 获取真实框的中心,也即是在网络输出上的网格左上角坐标
# np.floor:返回的是不大于当前值的最大整数,也就是左上角坐标
xind, yind = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32)
print("yind, xind: ", xind, yind)
# label[i].shape: (output_size, output_size, anchor_per_scale, 5+num_class)
# 初始化全用零填充
label[i][yind, xind, iou_mask, :] = 0
# print(label[i][yind, xind])
# 网格(yind,xind)处有目标, 填充真实框的中心和宽高
label[i][yind, xind, iou_mask, 0:4] = bbox_xywh
# 设置置信度为1.0, 表面有目标
label[i][yind, xind, iou_mask, 4:5] = 1.0
label[i][yind, xind, iou_mask, 5:] = smooth_onehot
print("label:\n", label[i].shape)
print(label[i][yind, xind])
# 假设iou_mask=[True,True,False],则填充如下：
# [[260.5 130.5 153. 147. 1. 1.]
# [260.5 130.5 153. 147. 1. 1.]
# [0. 0. 0. 0. 0. 0.]]
# exit()
# label[i].shape: (72, 72, 3, 6)
# 计算真实框的索引, 根据场景的真实标签,可以调整数值大小
bbox_ind = int(bbox_count[i] % self.max_bbox_per_scale)
bboxes_xywh[i][bbox_ind, :4] = bbox_xywh
# 记录该尺度下真实框的数量
bbox_count[i] += 1
exist_positive = True
print('===============================')
# iou < 0.3 执行此处处理,则选取最大的IOU，作为正样本.
if not exist_positive:
print('+++++++++++++++++++++++++++')
best_anchor_ind = np.argmax(np.array(iou).reshape(-1), axis=-1)
best_detect = int(best_anchor_ind / self.anchor_per_scale)
best_anchor = int(best_anchor_ind % self.anchor_per_scale)
xind, yind = np.floor(bbox_xywh_scaled[best_detect, 0:2]).astype(np.int32)
label[best_detect][yind, xind, best_anchor, :] = 0
label[best_detect][yind, xind, best_anchor, 0:4] = bbox_xywh
label[best_detect][yind, xind, best_anchor, 4:5] = 1.0
label[best_detect][yind, xind, best_anchor, 5:] = smooth_onehot
bbox_ind = int(bbox_count[best_detect] % self.max_bbox_per_scale)
bboxes_xywh[best_detect][bbox_ind, :4] = bbox_xywh
bbox_count[best_detect] += 1
# print('label shape: ', len(label))
# print(label[0].shape)
# print(len(label))
# 5+num_class：存放三种尺度下中心坐标,宽高,置信度,类别概率
# label shape：(3, output_size, output_size, anchor_per_scale, 5+num_class)
label_sbbox, label_mbbox, label_lbbox = label
# bboxes: 存放真实框的中心和宽高坐标
# shape: (3, 150, 4)
# 3: 3种尺度；150：每种尺度下最大的真实框的数量；4：（x,y,w,h）
sbboxes, mbboxes, lbboxes = bboxes_xywh
return label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes