YOLOv3_01_dataset.py

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
        #TRAIN=./data/dataset/yymnist_train.txt" ，cfg.TRAIN.ANNOT_PATH的地址
        #TEST =./data/dataset/yymnist_test.txt" 
        #yyminst为简化的数字目标检测数据集
        
        self.input_sizes = cfg.TRAIN.INPUT_SIZE if dataset_type == 'train' else cfg.TEST.INPUT_SIZE
        #TRAIN  self.input_sizes = 416
        #TEST   self.input_sizes = 544
        
        self.batch_size  = cfg.TRAIN.BATCH_SIZE if dataset_type == 'train' else cfg.TEST.BATCH_SIZE
        #TRAIN self.batch_size = 4
        #TEST  self.batch_size = 2
        
        self.data_aug    = cfg.TRAIN.DATA_AUG   if dataset_type == 'train' else cfg.TEST.DATA_AUG
        #TRAIN=True  参数可训练
        #TEST =False 参数冻结不可训练

        self.train_input_sizes = cfg.TRAIN.INPUT_SIZE #  416
        self.strides = np.array(cfg.YOLO.STRIDES)    #   [8, 16, 32]
        self.classes = utils.read_class_names(cfg.YOLO.CLASSES)
        #self.classes = 1 2 3 4 5 6 7 8 9 0 十个数字
        
        self.num_classes = len(self.classes)#[10]
        
        self.anchors = np.array(utils.get_anchors(cfg.YOLO.ANCHORS))#[3,3,2]
        #anchors =1.25,1.625, 2.0,3.75, 4.125,2.875,     1.875,3.8125, 3.875,2.8125, 3.6875,7.4375,     3.625,2.8125, 4.875,6.1875, 11.65625,10.1875
        #anchors通过聚类求出，可以加快训练速度，但对最终训练精度无影响
        #anchors分为三个步长，每个步长包含三个尺寸的边框，实现不同精度的检验
        
        self.anchor_per_scale = cfg.YOLO.ANCHOR_PER_SCALE # 3
        self.max_bbox_per_scale = 150 #每个尺寸下最多有150个待选框

        self.annotations = self.load_annotations(dataset_type) #获取注释文件信息
        self.num_samples = len(self.annotations) #样本数量,假设 数量=1000
        self.num_batchs = int(np.ceil(self.num_samples / self.batch_size))
        #np.ceil向上取整，一个batch取多少样本 int（1000/4）=250
        
'''#np.ceil向上取整
>>> a = np.array([-1.7, -1.5, -0.2, 0.2, 1.5, 1.7, 2.0])
>>> np.ceil(a)
array([-1., -1., -0.,  1.,  2.,  2.,  2.])
'''
        self.batch_count = 0 

def load_annotations(self, dataset_type):
        with open(self.annot_path, 'r') as f:
            txt = f.readlines() #读取行内容
            annotations = [line.strip() for line in txt if len(line.strip().split()[1:]) != 0]

        np.random.shuffle(annotations)#打乱顺序

    def __iter__(self):
        return self

    def __next__(self):

        with tf.device('/cpu:0'):
            self.train_input_size = self.train_input_sizes #416
            self.train_output_sizes = self.train_input_size // self.strides 
            # 416/[8，16，32]=[52,26,13]

            batch_image = np.zeros((self.batch_size, self.train_input_size, self.train_input_size, 3), dtype=np.float32)#[4,416,416,3] 填充0
            
            #small_bounding_box = sbbox
            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), dtype=np.float32)#[4,52,52,3,85]  填充0
            #middle_bounding_box = mbbox
            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), dtype=np.float32)#[4,26,26,3,85]  填充0
            #large_bounding_box = lbbox
            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), dtype=np.float32)#[4,13,13,3,85]  填充0

            batch_sbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4), dtype=np.float32)# [4,150,4] 填充0
            batch_mbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4), dtype=np.float32)# [4,150,4] 填充0
            batch_lbboxes = np.zeros((self.batch_size, self.max_bbox_per_scale, 4), dtype=np.float32)# [4,150,4] 填充0

            num = 0
            #############################################################
            '''加深一下印象
            self.batch_count=0
            self.batch_size =    #TRAIN=4     #TEST =2
            self.num_samples = len(self.annotations) #样本数量,假设=1000
            self.num_batchs = int(np.ceil(self.num_samples / self.batch_size))#np.ceil向上取整，一个batch取多少样本 int（800/4）=200
            num = 0
            
            '''加深一下印象
            ##############################################################
            if self.batch_count < self.num_batchs:#self.num_batchs = int(np.ceil(self.num_samples / self.batch_size))
                                                  #np.ceil向上取整，一个batch取多少样本 int（800/4）=200
                
                while num < self.batch_size: #self.batch_size:  TRAIN=4  TEST =2
                    index = self.batch_count * self.batch_size + num
                    if index >= self.num_samples: index -= self.num_samples #num_samples 样本数量,假设=1000
                    annotation = self.annotations[index]  #样本信息
                    #annotation[n]的格式如下，图片地址+box1的位置（x1,y1,x2,y2)和类别+……boxn的位置和类别
                    #/home/yang/test/TensorFlow2.0-Examples/4-Object_Detection/YOLOV3/data/dataset/test/000005.jpg 194,13,216,35,9 126,34,168,76,2 80,183,108,211,6 341,332,397,388,6

                    image, bboxes = self.parse_annotation(annotation)#parse 英 [pɑːz] 美 [pɑːrs] :分析

                    label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes = self.preprocess_true_boxes(bboxes)#预处理
                    #small 52,     middle 26,       large 13,

                    batch_image[num, :, :, :] = image#将样本image填入 batch_image [4,416,416,3]
                    batch_label_sbbox[num, :, :, :, :] = label_sbbox#[4,52,52,3,85] feature map
                    batch_label_mbbox[num, :, :, :, :] = label_mbbox#[4,26,26,3,85]
                    batch_label_lbbox[num, :, :, :, :] = label_lbbox#[4,13,13,3,85]
                    batch_sbboxes[num, :, :] = sbboxes# [4,150,4]
                    batch_mbboxes[num, :, :] = mbboxes# [4,150,4]
                    batch_lbboxes[num, :, :] = lbboxes# [4,150,4] 4=batch_size   150=最多的bounding_box的数量  4=x1,y1,x2,y2边框的位置

                    
                    num += 1
                self.batch_count += 1
                batch_smaller_target = batch_label_sbbox, batch_sbboxes#([4,52,52,3,85],[4,150,4])
                batch_medium_target  = batch_label_mbbox, batch_mbboxes#([4,26,26,3,85],[4,150,4])
                batch_larger_target  = batch_label_lbbox, batch_lbboxes#([4,13,13,3,85],[4,150,4])

                return batch_image, (batch_smaller_target, batch_medium_target, batch_larger_target)
            else:
                self.batch_count = 0
                np.random.shuffle(self.annotations)#随机打乱顺序
                raise StopIteration 

    def random_horizontal_flip(self, image, bboxes):#图片翻转

        if random.random() < 0.5:
            _, w, _ = image.shape
            image = image[:, ::-1, :]#水平翻转
            bboxes[:, [0,2]] = w - bboxes[:, [2,0]]   # [0,2]=[左上角x1,右下角x2] w=图片宽度
            # [num,5] 例：194,13,216,35,9    126,34,168,76,2    80,183,108,211,6     341,332,397,388,6
            
        return image, bboxes

    def random_crop(self, image, bboxes):#随机裁剪

        if random.random() < 0.5:
            h, w, _ = image.shape
            max_bbox = np.concatenate([np.min(bboxes[:, 0:2], axis=0), np.max(bboxes[:, 2:4], axis=0)], axis=-1)


            max_l_trans = max_bbox[0]
            max_u_trans = max_bbox[1]
            max_r_trans = w - max_bbox[2]
            max_d_trans = h - max_bbox[3]

            crop_xmin = max(0, int(max_bbox[0] - random.uniform(0, max_l_trans)))#random.uniform(x, y) 方法将随机生成一个实数，它在 [x,y] 范围内。
            crop_ymin = max(0, int(max_bbox[1] - random.uniform(0, max_u_trans)))
            crop_xmax = max(w, int(max_bbox[2] + random.uniform(0, max_r_trans)))
            crop_ymax = max(h, int(max_bbox[3] + random.uniform(0, max_d_trans)))

            image = image[crop_ymin : crop_ymax, crop_xmin : crop_xmax]

            bboxes[:, [0, 2]] = bboxes[:, [0, 2]] - crop_xmin
            bboxes[:, [1, 3]] = bboxes[:, [1, 3]] - crop_ymin

        return image, bboxes

    def random_translate(self, image, bboxes):

        if random.random() < 0.5:
            h, w, _ = image.shape
            max_bbox = np.concatenate([np.min(bboxes[:, 0:2], axis=0), np.max(bboxes[:, 2:4], axis=0)], axis=-1)
            #数组拼接
            max_l_trans = max_bbox[0]
            max_u_trans = max_bbox[1]
            max_r_trans = w - max_bbox[2]
            max_d_trans = h - max_bbox[3]

            tx = random.uniform(-(max_l_trans - 1), (max_r_trans - 1))
            ty = random.uniform(-(max_u_trans - 1), (max_d_trans - 1))

            M = np.array([[1, 0, tx], [0, 1, ty]])
            image = cv2.warpAffine(image, M, (w, h)) #opencv中的仿射变换

            bboxes[:, [0, 2]] = bboxes[:, [0, 2]] + tx
            bboxes[:, [1, 3]] = bboxes[:, [1, 3]] + ty

    def parse_annotation(self, annotation):#注释的语法分析

        line = annotation.split()
        #分隔符为空格，annotation格式如下
        #/home/yang/test/TensorFlow2.0-Examples/4-Object_Detection/YOLOV3/data/dataset/test/000005.jpg 194,13,216,35,9 126,34,168,76,2 80,183,108,211,6 341,332,397,388,6

        
        image_path = line[0]
        #/home/yang/test/TensorFlow2.0-Examples/4-Object_Detection/YOLOV3/data/dataset/test/000005.jpg
        
        if not os.path.exists(image_path):
            raise KeyError("%s does not exist ... " %image_path)
        image = cv2.imread(image_path)
        bboxes = np.array([list(map(int, box.split(','))) for box in line  [1:]])#194,13,216,35,9   126,34,168,76,2   80,183,108,211,6   341,332,397,388,6

        if self.data_aug:
            #TRAIN=True
            #TEST =False
            image, bboxes = self.random_horizontal_flip(np.copy(image), np.copy(bboxes))#水平翻转
            image, bboxes = self.random_crop(np.copy(image), np.copy(bboxes))#随机裁剪
            image, bboxes = self.random_translate(np.copy(image), np.copy(bboxes))#仿射变换

        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) #cv2读取的图片，默认为BGR,需要转换成RGB
        image, bboxes = utils.image_preporcess(np.copy(image), [self.train_input_size, self.train_input_size], np.copy(bboxes))
        #utils.image_preporcess(np.copy(image)将图片处理成[416,416,3]大小，简单的拉伸会使图片失真降低模型精度
        
        return image, bboxes

    def bbox_iou(self, boxes1, boxes2):

        boxes1 = np.array(boxes1)
        boxes2 = np.array(boxes2)  #shape= [3，4]

        boxes1_area = boxes1[..., 2] * boxes1[..., 3]#boxes1的面积
        boxes2_area = boxes2[..., 2] * boxes2[..., 3]

        boxes1 = np.concatenate([boxes1[..., :2] - boxes1[..., 2:] * 0.5,
                                boxes1[..., :2] + boxes1[..., 2:] * 0.5], axis=-1)# 左上角和右下角的坐标
        boxes2 = np.concatenate([boxes2[..., :2] - boxes2[..., 2:] * 0.5,
                                boxes2[..., :2] + boxes2[..., 2:] * 0.5], axis=-1)

        left_up = np.maximum(boxes1[..., :2], boxes2[..., :2])
        right_down = np.minimum(boxes1[..., 2:], boxes2[..., 2:])#交集

        inter_section = np.maximum(right_down - left_up, 0.0)# 交集的长宽
        inter_area = inter_section[..., 0] * inter_section[..., 1]#交集的面积
        union_area = boxes1_area + boxes2_area - inter_area#并集的面积

        return inter_area / union_area

def preprocess_true_boxes(self, bboxes):
        #selt.train_output_size=[52,26,13]
        #self.anchor_per_scale=3
        #self.num_classes=80
        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)]
        #shape=[52,52,3,85],[26,26,3,85],[13,13,3,85]
        
        bboxes_xywh = [np.zeros((self.max_bbox_per_scale, 4)) for _ in range(3)]#[150,4],[150,4],[150,4]
        bbox_count = np.zeros((3,))#[0,0,0]

        for bbox in bboxes:
            bbox_coor = bbox[:4] #coordinate 坐标
            bbox_class_ind = bbox[4]

            onehot = np.zeros(self.num_classes, dtype=np.float)#[0,0,0,0,0,0,0,0,0,0]
            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

            bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5, bbox_coor[2:] - bbox_coor[:2]], axis=-1)
            bbox_xywh_scaled = 1.0 * bbox_xywh[np.newaxis, :] / self.strides[:, np.newaxis]
            
            iou = []
            exist_positive = False
            for i in range(3):
                anchors_xywh = np.zeros((self.anchor_per_scale, 4))  #[3,4]
                anchors_xywh[:, 0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5#坐标 
                
                #np.floor 用法举例
                #n = np.array([-1.7, -2.5, -0.2, 0.6, 1.2, 2.7, 11]) 
                #floor = np.floor(n)
                #print(floor)  
                #输出 [ -2.  -3.  -1.   0.   1.   2.  11.]

                
                anchors_xywh[:, 2:4] = self.anchors[i]#[3,3,2] bounding_box's lenth ans width

                iou_scale = self.bbox_iou(bbox_xywh_scaled[i][np.newaxis, :], anchors_xywh)
                iou.append(iou_scale)
                iou_mask = iou_scale > 0.3

                if np.any(iou_mask):
                    xind, yind = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32)

                    label[i][yind, xind, iou_mask, :] = 0
                    label[i][yind, xind, iou_mask, 0:4] = bbox_xywh
                    label[i][yind, xind, iou_mask, 4:5] = 1.0
                    label[i][yind, xind, iou_mask, 5:] = smooth_onehot

                    bbox_ind = int(bbox_count[i] % self.max_bbox_per_scale)
                    bboxes_xywh[i][bbox_ind, :4] = bbox_xywh
                    bbox_count[i] += 1

                    exist_positive = True

            if not exist_positive:
                best_anchor_ind = np.argmax(np.array(iou).reshape(-1), axis=-1)#取出元素最大值所对应的索引
                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
        label_sbbox, label_mbbox, label_lbbox = label
        sbboxes, mbboxes, lbboxes = bboxes_xywh
        return label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes

    def __len__(self):
        return self.num_batchs

def __len__(self):
        return self.num_batchs