COCO数据集目标检测任务EDA模板

该内容围绕小麦和昆虫检测数据集展开探索性数据分析（EDA）。先进行环境准备与数据集解压，接着分析数据整体分布，涵盖图片数量、类别、尺寸等，还探究了图像分辨率、亮度、目标分布、单张图片目标情况、目标遮挡及颜色等，最后实现了VOC到COCO格式的转换。

1 环境准备

In [1]

# 调用一些需要的第三方库import numpy as npimport pandas as pdimport shutilimport jsonimport osimport cv2import globimport matplotlib.pyplot as pltimport matplotlib.patches as patchesimport seaborn as snsfrom matplotlib.font_manager import FontPropertiesfrom PIL import Imageimport randommyfont = FontProperties(fname=r"NotoSansCJKsc-Medium.otf", size=12)plt.rcParams['figure.figsize'] = (12, 12)plt.rcParams['font.family']= myfont.get_family()plt.rcParams['font.sans-serif'] = myfont.get_name()plt.rcParams['axes.unicode_minus'] = False

登录后复制    In [3]

# !unzip data/data54680/coco.zip

登录后复制    In [5]

!unzip data/data42353/wheat.zip

登录后复制    In [2]

# Setup the paths to train and test imagesTRAIN_DIR = 'wheat/train/'TRAIN_CSV_PATH = 'wheat/train.json'# Glob the directories and get the lists of train and test imagestrain_fns = glob.glob(TRAIN_DIR + '*')print('数据集图片数量: {}'.format(len(train_fns)))

登录后复制        

数据集图片数量: 3422

登录后复制        

2 数据整体分布情况

In [7]

def generate_anno_eda(dataset_path, anno_file):    with open(os.path.join(dataset_path, anno_file)) as f:        anno = json.load(f)    print('标签类别:', anno['categories'])    print('类别数量：', len(anno['categories']))    print('训练集图片数量：', len(anno['images']))    print('训练集标签数量：', len(anno['annotations']))        total=[]    for img in anno['images']:        hw = (img['height'],img['width'])        total.append(hw)    unique = set(total)    for k in unique:        print('长宽为(%d,%d)的图片数量为：'%k,total.count(k))        ids=[]    images_id=[]    for i in anno['annotations']:        ids.append(i['id'])        images_id.append(i['image_id'])    print('训练集图片数量:', len(anno['images']))    print('unique id 数量：', len(set(ids)))    print('unique image_id 数量', len(set(images_id)))        # 创建类别标签字典    category_dic=dict([(i['id'],i['name']) for i in anno['categories']])    counts_label=dict([(i['name'],0) for i in anno['categories']])    for i in anno['annotations']:        counts_label[category_dic[i['category_id']]] += 1    label_list = counts_label.keys()    # 各部分标签    print('标签列表:', label_list)    size = counts_label.values()    # 各部分大小    color = ['#FFB6C1', '#D8BFD8', '#9400D3', '#483D8B', '#4169E1', '#00FFFF','#B1FFF0','#ADFF2F','#EEE8AA','#FFA500','#FF6347']     # 各部分颜色    # explode = [0.05, 0, 0]   # 各部分突出值    patches, l_text, p_text = plt.pie(size, labels=label_list, colors=color, labeldistance=1.1, autopct="%1.1f%%", shadow=False, startangle=90, pctdistance=0.6, textprops={'fontproperties':myfont})    plt.axis("equal")    # 设置横轴和纵轴大小相等，这样饼才是圆的    plt.legend(prop=myfont)    plt.show()

登录后复制    In [9]

# 分析训练集数据generate_anno_eda('wheat', 'train.json')

登录后复制    

2.1 图片整体分析

2.1.1 图像分辨率

In [3]

# 读取训练集标注文件with open(TRAIN_CSV_PATH, 'r', encoding='utf-8') as f:    train_data = json.load(f)train_fig = pd.DataFrame(train_data['images'])

登录后复制    In [4]

train_fig.head()

登录后复制        

       file_name  height  id  width0  b6ab77fd7.jpg    1024   1   10241  b53afdf5c.jpg    1024   2   10242  7b72ea0fb.jpg    1024   3   10243  91c9d9c38.jpg    1024   4   10244  41c0123cc.jpg    1024   5   1024

登录后复制                In [16]

ps = np.zeros(len(train_fig))for i in range(len(train_fig)):    ps[i]=train_fig['width'][i] * train_fig['height'][i]/1e6plt.title('训练集图片大小分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制    In [5]

train_anno = pd.DataFrame(train_data['annotations'])df_train = pd.merge(left=train_fig, right=train_anno, how='inner', left_on='id', right_on='image_id')df_train['bbox_xmin'] = df_train['bbox'].apply(lambda x: x[0])df_train['bbox_ymin'] = df_train['bbox'].apply(lambda x: x[1])df_train['bbox_w'] = df_train['bbox'].apply(lambda x: x[2])df_train['bbox_h'] = df_train['bbox'].apply(lambda x: x[3])df_train['bbox_xcenter'] = df_train['bbox'].apply(lambda x: (x[0]+0.5*x[2]))df_train['bbox_ycenter'] = df_train['bbox'].apply(lambda x: (x[1]+0.5*x[3]))

登录后复制    In [18]

def get_all_bboxes(df, name):    image_bboxes = df[df.file_name == name]        bboxes = []    categories = []    for _,row in image_bboxes.iterrows():        bboxes.append((row.bbox_xmin, row.bbox_ymin, row.bbox_w, row.bbox_h, row.category_id))    return bboxesdef plot_image_examples(df, rows=3, cols=3, title="Image examples"):    fig, axs = plt.subplots(rows, cols, figsize=(15,15))    color = ['#FFB6C1', '#D8BFD8', '#9400D3', '#483D8B', '#4169E1', '#00FFFF','#B1FFF0','#ADFF2F','#EEE8AA','#FFA500','#FF6347']     # 各部分颜色    for row in range(rows):        for col in range(cols):            idx = np.random.randint(len(df), size=1)[0]            name = df.iloc[idx]["file_name"]            img = Image.open(TRAIN_DIR + str(name))            axs[row, col].imshow(img)                        bboxes = get_all_bboxes(df, name)            for bbox in bboxes:                rect = patches.Rectangle((bbox[0],bbox[1]),bbox[2],bbox[3],linewidth=1,edgecolor=color[bbox[4]],facecolor='none')                axs[row, col].add_patch(rect)                        axs[row, col].axis('off')                plt.suptitle(title,fontproperties=myfont)

登录后复制    In [19]

def plot_gray_examples(df, rows=3, cols=3, title="Image examples"):    fig, axs = plt.subplots(rows, cols, figsize=(15,15))    color = ['#FFB6C1', '#D8BFD8', '#9400D3', '#483D8B', '#4169E1', '#00FFFF','#B1FFF0','#ADFF2F','#EEE8AA','#FFA500','#FF6347']     # 各部分颜色    for row in range(rows):        for col in range(cols):            idx = np.random.randint(len(df), size=1)[0]            name = df.iloc[idx]["file_name"]            img = Image.open(TRAIN_DIR + str(name)).convert('L')            axs[row, col].imshow(img)                        bboxes = get_all_bboxes(df, name)            for bbox in bboxes:                rect = patches.Rectangle((bbox[0],bbox[1]),bbox[2],bbox[3],linewidth=1,edgecolor=color[bbox[4]],facecolor='none')                axs[row, col].add_patch(rect)                        axs[row, col].axis('off')                plt.suptitle(title,fontproperties=myfont)

登录后复制    

2.1.2 图像亮度分析

In [20]

def get_image_brightness(image):    # convert to grayscale    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)        # get average brightness    return np.array(gray).mean()def add_brightness(df):    brightness = []    for _, row in df.iterrows():            name = row["file_name"]        image = cv2.imread(TRAIN_DIR + name)        brightness.append(get_image_brightness(image))            brightness_df = pd.DataFrame(brightness)    brightness_df.columns = ['brightness']    df = pd.concat([df, brightness_df], ignore_index=True, axis=1)    df.columns = ['file_name', 'brightness']        return dfimages_df = pd.DataFrame(df_train.file_name.unique())images_df.columns = ['file_name']brightness_df = add_brightness(images_df)

登录后复制    In [22]

brightness_df.head()

登录后复制    In [23]

dark_names = brightness_df[brightness_df['brightness'] < 50].file_nameplot_image_examples(df_train[df_train.file_name.isin(dark_names)], title="暗图片")

登录后复制        

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/font_manager.py:1331: UserWarning: findfont: Font family ['sans-serif'] not found. Falling back to DejaVu Sans  (prop.get_family(), self.defaultFamily[fontext]))

登录后复制        

登录后复制登录后复制登录后复制登录后复制                In [24]

bright_names =  brightness_df[brightness_df['brightness'] > 130].file_nameplot_image_examples(df_train[df_train.file_name.isin(bright_names)], title="亮图片")

登录后复制    In [25]

sns.set(rc={'figure.figsize':(12,6)})ps = np.zeros(len(brightness_df))for i in range(len(brightness_df)):    ps[i]=brightness_df['brightness'][i]plt.title('图片亮度分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制        

登录后复制                

登录后复制登录后复制登录后复制登录后复制登录后复制登录后复制                

2.2 目标分布分析

In [26]

ps = np.zeros(len(df_train))for i in range(len(df_train)):    ps[i]=df_train['area'][i]/1e6plt.title('训练集目标大小分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制        

登录后复制                

登录后复制登录后复制登录后复制登录后复制登录后复制登录后复制                In [27]

# 各类别目标形状分布sns.set(rc={'figure.figsize':(12,6)})sns.relplot(x="bbox_w", y="bbox_h", hue="category_id", col="category_id", data=df_train[0:1000])

登录后复制        

登录后复制                

登录后复制登录后复制                In [28]

# 各类别目标中心点形状分布sns.set(rc={'figure.figsize':(12,6)})sns.relplot(x="bbox_xcenter", y="bbox_ycenter", hue="category_id", col="category_id", data=df_train[0:1000]);

登录后复制        

登录后复制登录后复制                In [30]

sns.set(rc={'figure.figsize':(12,6)})plt.title('训练集目标大小分布', fontproperties=myfont)sns.violinplot(x=df_train['category_id'],y=df_train['area'])

登录后复制    In [20]

df_train.area.describe()

登录后复制        

count    147793.000000mean       6843.356576std        5876.326590min           2.00000025%        3658.00000050%        5488.00000075%        8272.000000max      529788.000000Name: area, dtype: float64

登录后复制                In [33]

sns.set(rc={'figure.figsize':(12,6)})plt.title('训练集小目标分布', fontproperties=myfont)plt.ylim(0, 4000)sns.violinplot(x=df_train['category_id'],y=df_train['area'])

登录后复制    In [34]

sns.set(rc={'figure.figsize':(12,6)})plt.title('训练集大目标分布', fontproperties=myfont)plt.ylim(10000, max(df_train.area))sns.violinplot(x=df_train['category_id'],y=df_train['area'])

登录后复制    In [36]

graph=sns.countplot(data=df_train, x='category_id')graph.set_xticklabels(graph.get_xticklabels(), rotation=90)plt.title('各类别目标数量分布', fontproperties=myfont)for p in graph.patches:    height = p.get_height()    graph.text(p.get_x()+p.get_width()/2., height + 0.1,height ,ha="center")

登录后复制    

2.3 重点图片分析

2.3.1 单张图片目标数量分布

In [37]

df_train['bbox_count'] = df_train.apply(lambda row: 1 if any(row.bbox) else 0, axis=1)train_images_count = df_train.groupby('file_name').sum().reset_index()

登录后复制    In [38]

train_images_count['bbox_count'].describe()

登录后复制        

count    3373.000000mean       43.816484std        20.374820min         1.00000025%        28.00000050%        43.00000075%        59.000000max       116.000000Name: bbox_count, dtype: float64

登录后复制                In [39]

# 目标数量超过50个的图片train_images_count['file_name'][train_images_count['bbox_count']>50]

登录后复制        

0       00333207f.jpg7       00ea5e5ee.jpg17      015939012.jpg23      02640d9da.jpg24      026b6f389.jpg            ...      3356    feac3a701.jpg3360    feda9265c.jpg3366    ffaa964a2.jpg3368    ffb445410.jpg3369    ffbf75e5b.jpgName: file_name, Length: 1272, dtype: object

登录后复制登录后复制                In [40]

# 目标数量超过100个的图片train_images_count['file_name'][train_images_count['bbox_count']>50]

登录后复制        

0       00333207f.jpg7       00ea5e5ee.jpg17      015939012.jpg23      02640d9da.jpg24      026b6f389.jpg            ...      3356    feac3a701.jpg3360    feda9265c.jpg3366    ffaa964a2.jpg3368    ffb445410.jpg3369    ffbf75e5b.jpgName: file_name, Length: 1272, dtype: object

登录后复制登录后复制                In [41]

less_spikes_ids = train_images_count[train_images_count['bbox_count'] > 50].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="单图目标超过50个（示例）")

登录后复制    In [42]

less_spikes_ids = train_images_count[train_images_count['bbox_count'] > 100].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="单图目标超过100个（示例）")

登录后复制    In [44]

less_spikes_ids = train_images_count[train_images_count['bbox_count'] < 5].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="单图目标少于5个（示例）")

登录后复制    

2.3.2 单图目标覆盖分析

In [45]

less_spikes_ids = train_images_count[train_images_count['area'] > max(train_images_count['area'])*0.9].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标总面积最大（示例）")

登录后复制    In [46]

less_spikes_ids = train_images_count[train_images_count['area'] < min(train_images_count['area'])*1.1].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标总面积最小（示例）")

登录后复制    

2.3.3 超大/极小目标分析

In [50]

df_train['bbox_count'] = df_train.apply(lambda row: 1 if any(row.bbox) else 0, axis=1)train_images_count = df_train.groupby('file_name').max().reset_index()less_spikes_ids = train_images_count[train_images_count['area'] > max(train_images_count['area'])*0.8].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="单目标面积最大（示例）")

登录后复制    In [49]

df_train['bbox_count'] = df_train.apply(lambda row: 1 if any(row.bbox) else 0, axis=1)train_images_count = df_train.groupby('file_name').min().reset_index()less_spikes_ids = train_images_count[train_images_count['area'] > min(train_images_count['area'])*1.2].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="单目标面积最小（示例）")

登录后复制        

登录后复制登录后复制登录后复制登录后复制                

2.4 目标遮挡分析

In [51]

# 计算IOUdef bb_intersection_over_union(boxA, boxB):    boxA = [int(x) for x in boxA]    boxB = [int(x) for x in boxB]    boxA = [boxA[0], boxA[1], boxA[0]+boxA[2], boxA[1]+boxA[3]]    boxB = [boxB[0], boxB[1], boxB[0]+boxB[2], boxB[1]+boxB[3]]    xA = max(boxA[0], boxB[0])    yA = max(boxA[1], boxB[1])    xB = min(boxA[2], boxB[2])    yB = min(boxA[3], boxB[3])    interArea = max(0, xB - xA + 1) * max(0, yB - yA + 1)    boxAArea = (boxA[2] - boxA[0] + 1) * (boxA[3] - boxA[1] + 1)    boxBArea = (boxB[2] - boxB[0] + 1) * (boxB[3] - boxB[1] + 1)        iou = interArea / float(boxAArea + boxBArea - interArea)    return iou

登录后复制    In [52]

# tmp 是一个pandas Series，且索引从0开始def bbox_iou(tmp):    iou_agg = 0    iou_cnt = 0    for i in range(len(tmp)):        for j in range(len(tmp)):            if i != j:                iou_agg += bb_intersection_over_union(tmp[i], tmp[j])                if bb_intersection_over_union(tmp[i], tmp[j]) > 0:                    iou_cnt += 1    iou_agg = iou_agg/2    iou_cnt = iou_cnt/2    return iou_agg, iou_cnt

登录后复制    In [53]

file_list = df_train['file_name'].unique()

登录后复制    In [ ]

train_iou_cal = pd.DataFrame(columns=('file_name', 'iou_agg', 'iou_cnt'))for i in range(len(file_list)):    tmp = df_train['bbox'][df_train.file_name==file_list[i]].reset_index(drop=True)    iou_agg, iou_cnt = bbox_iou(tmp)    train_iou_cal.loc[len(train_iou_cal)] = [file_list[i], iou_agg, iou_cnt]

登录后复制    In [ ]

train_iou_cal.iou_agg.describe()

登录后复制    In [ ]

ps = np.zeros(len(train_iou_cal))for i in range(len(train_iou_cal)):    ps[i]=train_iou_cal['iou_agg'][i]plt.title('训练集目标遮挡程度分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制    In [ ]

train_iou_cal.iou_cnt.describe()

登录后复制    In [ ]

ps = np.zeros(len(train_iou_cal))for i in range(len(train_iou_cal)):    ps[i]=train_iou_cal['iou_cnt'][i]plt.title('训练集目标遮挡数量分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制    In [ ]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_agg'] > max(train_iou_cal['iou_agg'])*0.9].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡程度最高（示例）")

登录后复制    In [55]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_agg'] <= min(train_iou_cal['iou_agg'])*1.1].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡程度最低（示例）")

登录后复制    In [56]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_cnt'] > max(train_iou_cal['iou_cnt'])*0.9].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡数量最高（示例）")

登录后复制    In [57]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_cnt'] <= min(train_iou_cal['iou_cnt'])*1.1].file_nameplot_image_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡数量最低（示例）")

登录后复制    

2.5 颜色分析

2.5.1 图像RGB分布

In [78]

files = os.listdir(TRAIN_DIR)R = 0.G = 0.B = 0.R_2 = 0.G_2 = 0.B_2 = 0.N = 0for f in files:    img = cv2.imread(TRAIN_DIR+f)    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)    img = np.array(img)    h, w, c = img.shape    N += h*w    R_t = img[:, :, 0]    R += np.sum(R_t)    R_2 += np.sum(np.power(R_t, 2.0))    G_t = img[:, :, 1]    G += np.sum(G_t)    G_2 += np.sum(np.power(G_t, 2.0))    B_t = img[:, :, 2]    B += np.sum(B_t)    B_2 += np.sum(np.power(B_t, 2.0))R_mean = R/NG_mean = G/NB_mean = B/NR_std = np.sqrt(R_2/N - R_mean*R_mean)G_std = np.sqrt(G_2/N - G_mean*G_mean)B_std = np.sqrt(B_2/N - B_mean*B_mean)print("R_mean: %f, G_mean: %f, B_mean: %f" % (R_mean, G_mean, B_mean))print("R_std: %f, G_std: %f, B_std: %f" % (R_std, G_std, B_std))

登录后复制        

R_mean: 80.398947, G_mean: 80.899598, B_mean: 54.711709R_std: 62.528853, G_std: 60.699236, B_std: 49.439114

登录后复制        

2.5.2 目标RGB分析

In [12]

# 计算bbox的RGBdef bb_rgb_cal(img, boxA):    boxA = [int(x) for x in boxA]    boxA = [boxA[0], boxA[1], boxA[0]+boxA[2], boxA[1]+boxA[3]]    img = img.crop(boxA)    width = img.size[0]    height = img.size[1]    img = img.convert('RGB')    array = []    for x in range(width):        for y in range(height):            r, g, b = img.getpixel((x,y))            rgb = (r, g, b)            array.append(rgb)    return round(np.mean(array[0]),2), round(np.mean(array[1]),2), round(np.mean(array[2]),2)

登录后复制    In [56]

# 可能遇到jupyter输出内存报错from tqdm import tqdmdf_train['r_channel'] = 0df_train['g_channel'] = 0df_train['b_channel'] = 0for i in tqdm(df_train.index):    array = bb_rgb_cal(Image.open(TRAIN_DIR + str(df_train.file_name[i])), df_train.bbox[i])    df_train['r_channel'].at[i] = array[0]    df_train['g_channel'].at[i] = array[1]    df_train['b_channel'].at[i] = array[2]

登录后复制    In [74]

ps = np.zeros(len(df_train[:10000]))for i in range(len(df_train[:10000])):    ps[i]=df_train['r_channel'][df_train.category_id==1][i]plt.title('类别1目标r_channel分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制        

登录后复制                

登录后复制登录后复制登录后复制登录后复制登录后复制登录后复制                In [75]

ps = np.zeros(len(df_train[:10000]))for i in range(len(df_train[:10000])):    ps[i]=df_train['g_channel'][df_train.g_channel>0][df_train.category_id==1][i]plt.title('类别1目标g_channel分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制        

登录后复制                

登录后复制登录后复制登录后复制登录后复制登录后复制登录后复制                In [76]

ps = np.zeros(len(df_train[:10000]))for i in range(len(df_train[:10000])):    ps[i]=df_train['b_channel'][df_train.b_channel>0][df_train.category_id==1][i]plt.title('类别1目标b_channel分布', fontproperties=myfont)sns.distplot(ps, bins=21,kde=False)

登录后复制        

登录后复制                

登录后复制登录后复制登录后复制登录后复制登录后复制登录后复制                

2.5.3 灰度图效果

In [143]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_cnt'] > max(train_iou_cal['iou_cnt'])*0.8].file_nameplot_gray_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡数量最高（灰度）")

登录后复制        

登录后复制登录后复制登录后复制登录后复制                In [140]

less_spikes_ids = train_iou_cal[train_iou_cal['iou_cnt'] <= min(train_iou_cal['iou_cnt'])*1.1].file_nameplot_gray_examples(df_train[df_train.file_name.isin(less_spikes_ids)], title="目标遮挡数量最低（灰度）")

登录后复制        

登录后复制登录后复制登录后复制登录后复制                

3 VOC数据集格式转换

由于上面的EDA是基于COCO格式数据集开发的，为避免重复造轮子，分析VOC数据集时，这里使用脚本将VOC转为COCO格式数据。

In [86]

# 获取示例数据集!wget https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz# 解压数据集!tar -zxvf insect_det.tar.gz

登录后复制    In [80]

import xml.etree.ElementTree as ETimport osimport json coco = dict()coco['images'] = []coco['type'] = 'instances'coco['annotations'] = []coco['categories'] = [] category_set = dict()image_set = set() category_item_id = -1image_id = 20180000000annotation_id = 0 def addCatItem(name):    global category_item_id    category_item = dict()    category_item['supercategory'] = 'none'    category_item_id += 1    category_item['id'] = category_item_id    category_item['name'] = name    coco['categories'].append(category_item)    category_set[name] = category_item_id    return category_item_id def addImgItem(file_name, size):    global image_id    if file_name is None:        raise Exception('Could not find filename tag in xml file.')    if size['width'] is None:        raise Exception('Could not find width tag in xml file.')    if size['height'] is None:        raise Exception('Could not find height tag in xml file.')    image_id += 1    image_item = dict()    image_item['id'] = image_id    image_item['file_name'] = file_name    image_item['width'] = size['width']    image_item['height'] = size['height']    coco['images'].append(image_item)    image_set.add(file_name)    return image_id def addAnnoItem(object_name, image_id, category_id, bbox):    global annotation_id    annotation_item = dict()    annotation_item['segmentation'] = []    seg = []    # bbox[] is x,y,w,h    # left_top    seg.append(bbox[0])    seg.append(bbox[1])    # left_bottom    seg.append(bbox[0])    seg.append(bbox[1] + bbox[3])    # right_bottom    seg.append(bbox[0] + bbox[2])    seg.append(bbox[1] + bbox[3])    # right_top    seg.append(bbox[0] + bbox[2])    seg.append(bbox[1])     annotation_item['segmentation'].append(seg)     annotation_item['area'] = bbox[2] * bbox[3]    annotation_item['iscrowd'] = 0    annotation_item['ignore'] = 0    annotation_item['image_id'] = image_id    annotation_item['bbox'] = bbox    annotation_item['category_id'] = category_id    annotation_id += 1    annotation_item['id'] = annotation_id    coco['annotations'].append(annotation_item) def _read_image_ids(image_sets_file):    ids = []    with open(image_sets_file) as f:        for line in f:            ids.append(line.rstrip())    return ids """通过txt文件生成"""#split ='train' 'va' 'trainval' 'test'def parseXmlFiles_by_txt(data_dir,json_save_path,split='train'):    print("hello")    labelfile=split+".txt"    image_sets_file = data_dir + "/ImageSets/Main/"+labelfile    ids=_read_image_ids(image_sets_file)     for _id in ids:        xml_file=data_dir + f"/Annotations/{_id}.xml"         bndbox = dict()        size = dict()        current_image_id = None        current_category_id = None        file_name = None        size['width'] = None        size['height'] = None        size['depth'] = None         tree = ET.parse(xml_file)        root = tree.getroot()        if root.tag != 'annotation':            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))         # elem is , , ,