add tools for voc dataset to coco (#1348)

docs/advanced_tutorials/READER.md

@@ -34,8 +34,6 @@ PaddleDetection的数据处理模块是一个Python模块，所有代码逻辑
   ├── tests  # 单元测试模块
   │   ├── test_dataset.py # 对数据集解析、加载等进行单元测试
   │   │   ...
-  ├── tools  # 一些有用的工具
-  │   ├── x2coco.py       # 将其他数据集转换为COCO数据集格式
   ├── transform  # 数据预处理模块
   │   ├── batch_operators.py  # 定义各类基于批量数据的预处理算子
   │   ├── op_helper.py    # 预处理算子的辅助函数

docs/advanced_tutorials/TRANSFER_LEARNING.md

@@ -8,7 +8,7 @@ In transfer learning, if different dataset and the number of classes is used, th
 
 ### Use custom dataset
 
-Transfer learning needs custom dataset and annotation in COCO-format and VOC-format is supported now. The script converts the annotation from labelme or cityscape to COCO is provided in ```ppdet/data/tools/x2coco.py```. More details please refer to [READER](READER.md). After data preparation, update the data parameters in configuration file.
+Transfer learning needs custom dataset and annotation in COCO-format and VOC-format is supported now. The script converts the annotation from voc, labelme or cityscape to COCO is provided in ```tools/x2coco.py```. More details please refer to [READER](READER.md). After data preparation, update the data parameters in configuration file.
 
 
 1. COCO-format dataset, take [yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml#L66) for example, modify the COCODataSet in yolov3\_reader:

docs/advanced_tutorials/TRANSFER_LEARNING_cn.md

@@ -7,7 +7,7 @@
 
 ### 选择数据
 
-迁移学习需要使用自己的数据集，目前已支持COCO和VOC的数据标注格式，在```ppdet/data/tools/x2coco.py```中给出了labelme和cityscape标注格式转换为COCO格式的脚本，具体使用方式可以参考[自定义数据源](READER.md)。数据准备完成后，在配置文件中配置数据路径，对应修改reader中的路径参数即可。
+迁移学习需要使用自己的数据集，目前已支持COCO和VOC的数据标注格式，在```tools/x2coco.py```中给出了voc、labelme和cityscape标注格式转换为COCO格式的脚本，具体使用方式可以参考[自定义数据源](READER.md)。数据准备完成后，在配置文件中配置数据路径，对应修改reader中的路径参数即可。
 
 1. COCO数据集需要修改COCODataSet中的参数，以[yolov3\_darknet.yml](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/yolov3_darknet.yml#L66)为例，修改yolov3\_reader中的配置：
 

docs/tutorials/Custom_DataSet.md

@@ -15,26 +15,42 @@
 
 ### 方式一：将数据集转换为COCO格式
 
-在`./tools/`中提供了`x2coco.py`用于将labelme标注的数据集或cityscape数据集转换为COCO数据集:
+在`./tools/`中提供了`x2coco.py`用于将voc格式数据集、labelme标注的数据集或cityscape数据集转换为COCO数据集，例如:
+
+（1）labelmes数据转换为COCO格式：
 ```bash
-python ./ppdet/data/tools/x2coco.py \
+python tools/x2coco.py \
                 --dataset_type labelme \
                 --json_input_dir ./labelme_annos/ \
                 --image_input_dir ./labelme_imgs/ \
                 --output_dir ./cocome/ \
                 --train_proportion 0.8 \
                 --val_proportion 0.2 \
-                --test_proportion 0.0 \
+                --test_proportion 0.0
+```
+（2）voc数据转换为COCO格式：
+```bash
+python tools/x2coco.py \
+        --dataset_type voc \
+        --voc_anno_dir path/to/VOCdevkit/VOC2007/Annotations/ \
+        --voc_anno_list path/to/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt \
+        --voc_label_list dataset/voc/label_list.txt \
+        --voc_out_name voc_train.json
 ```
+
 **参数说明：**
 
-- `--dataset_type`：需要转换的数据格式，目前支持：’labelme‘和’cityscape‘
+- `--dataset_type`：需要转换的数据格式，目前支持：’voc‘、’labelme‘和’cityscape‘
 - `--json_input_dir`：使用labelme标注的json文件所在文件夹
 - `--image_input_dir`：图像文件所在文件夹
 - `--output_dir`：转换后的COCO格式数据集存放位置
 - `--train_proportion`：标注数据中用于train的比例
 - `--val_proportion`：标注数据中用于validation的比例
 - `--test_proportion`：标注数据中用于infer的比例
+- `--voc_anno_dir`：VOC数据转换为COCO数据集时的voc数据集标注文件路径
+- `--voc_anno_list`：VOC数据转换为COCO数据集时的标注列表文件，一般是`ImageSets/Main`下trainval.txt和test.txt文件
+- `--voc_label_list`：VOC数据转换为COCO数据集时的类别列表文件，文件中每一行表示一种物体类别
+- `--voc_out_name`：VOC数据转换为COCO数据集时的输出的COCO数据集格式json文件名
 
 ### 方式二：将数据集转换为VOC格式
 

ppdet/data/source/coco.py

@@ -137,14 +137,14 @@ class COCODataSet(DataSet):
                     y1 = max(0, y)
                     x2 = min(im_w - 1, x1 + max(0, box_w - 1))
                     y2 = min(im_h - 1, y1 + max(0, box_h - 1))
-                    if inst['area'] > 0 and x2 >= x1 and y2 >= y1:
+                    if x2 >= x1 and y2 >= y1:
                         inst['clean_bbox'] = [x1, y1, x2, y2]
                         bboxes.append(inst)
                     else:
                         logger.warn(
                             'Found an invalid bbox in annotations: im_id: {}, '
-                            'area: {} x1: {}, y1: {}, x2: {}, y2: {}.'.format(
-                                img_id, float(inst['area']), x1, y1, x2, y2))
+                            'x1: {}, y1: {}, x2: {}, y2: {}.'.format(
+                                img_id, x1, y1, x2, y2))
                 num_bbox = len(bboxes)
 
                 gt_bbox = np.zeros((num_bbox, 4), dtype=np.float32)

ppdet/data/tools/x2coco.py → tools/x2coco.py

@@ -21,6 +21,9 @@ import os
 import os.path as osp
 import sys
 import shutil
+import xml.etree.ElementTree as ET
+from tqdm import tqdm
+import re
 
 import numpy as np
 import PIL.ImageDraw
@@ -154,17 +157,19 @@ def deal_json(ds_type, img_path, json_path):
                         categories_list.append(categories(label, labels_list))
                         labels_list.append(label)
                         label_to_num[label] = len(labels_list)
-                    points = shapes['points']
                     p_type = shapes['shape_type']
                     if p_type == 'polygon':
+                        points = shapes['points']
                         annotations_list.append(
                             annotations_polygon(data['imageHeight'], data[
                                 'imageWidth'], points, label, image_num,
                                                 object_num, label_to_num))
 
                     if p_type == 'rectangle':
-                        points.append([points[0][0], points[1][1]])
-                        points.append([points[1][0], points[0][1]])
+                        (x1, y1), (x2, y2) = shapes['points']
+                        x1, x2 = sorted([x1, x2])
+                        y1, y2 = sorted([y1, y2])
+                        points = [[x1, y1], [x2, y2], [x1, y2], [x2, y1]]
                         annotations_list.append(
                             annotations_rectangle(points, label, image_num,
                                                   object_num, label_to_num))
@@ -187,6 +192,100 @@ def deal_json(ds_type, img_path, json_path):
     return data_coco
 
 
+def voc_get_label_anno(ann_dir_path, ann_ids_path, labels_path):
+    with open(labels_path, 'r') as f:
+        labels_str = f.read().split()
+    labels_ids = list(range(1, len(labels_str) + 1))
+
+    with open(ann_ids_path, 'r') as f:
+        ann_ids = f.read().split()
+    ann_paths = []
+    for aid in ann_ids:
+        if aid.endswith('xml'):
+            ann_path = os.path.join(ann_dir_path, aid)
+        else:
+            ann_path = os.path.join(ann_dir_path, aid + '.xml')
+        ann_paths.append(ann_path)
+
+    return dict(zip(labels_str, labels_ids)), ann_paths
+
+
+def voc_get_image_info(annotation_root, im_id):
+    filename = annotation_root.findtext('filename')
+    assert filename is not None
+    img_name = os.path.basename(filename)
+
+    size = annotation_root.find('size')
+    width = int(size.findtext('width'))
+    height = int(size.findtext('height'))
+
+    image_info = {
+        'file_name': filename,
+        'height': height,
+        'width': width,
+        'id': im_id
+    }
+    return image_info
+
+
+def voc_get_coco_annotation(obj, label2id):
+    label = obj.findtext('name')
+    assert label in label2id, "label is not in label2id."
+    category_id = label2id[label]
+    bndbox = obj.find('bndbox')
+    xmin = int(bndbox.findtext('xmin')) - 1
+    ymin = int(bndbox.findtext('ymin')) - 1
+    xmax = int(bndbox.findtext('xmax'))
+    ymax = int(bndbox.findtext('ymax'))
+    assert xmax > xmin and ymax > ymin, "Box size error."
+    o_width = xmax - xmin
+    o_height = ymax - ymin
+    anno = {
+        'area': o_width * o_height,
+        'iscrowd': 0,
+        'bbox': [xmin, ymin, o_width, o_height],
+        'category_id': category_id,
+        'ignore': 0,
+        'segmentation': []  # This script is not for segmentation
+    }
+    return anno
+
+
+def voc_xmls_to_cocojson(annotation_paths, label2id, output_dir, output_file):
+    output_json_dict = {
+        "images": [],
+        "type": "instances",
+        "annotations": [],
+        "categories": []
+    }
+    bnd_id = 1  # bounding box start id
+    im_id = 0
+    print('Start converting !')
+    for a_path in tqdm(annotation_paths):
+        # Read annotation xml
+        ann_tree = ET.parse(a_path)
+        ann_root = ann_tree.getroot()
+
+        img_info = voc_get_image_info(ann_root, im_id)
+        im_id += 1
+        img_id = img_info['id']
+        output_json_dict['images'].append(img_info)
+
+        for obj in ann_root.findall('object'):
+            ann = voc_get_coco_annotation(obj=obj, label2id=label2id)
+            ann.update({'image_id': img_id, 'id': bnd_id})
+            output_json_dict['annotations'].append(ann)
+            bnd_id = bnd_id + 1
+
+    for label, label_id in label2id.items():
+        category_info = {'supercategory': 'none', 'id': label_id, 'name': label}
+        output_json_dict['categories'].append(category_info)
+    output_file = os.path.join(output_dir, output_file)
+    with open(output_file, 'w') as f:
+        output_json = json.dumps(output_json_dict)
+        f.write(output_json)
+
+
 def main():
     parser = argparse.ArgumentParser(
         formatter_class=argparse.ArgumentDefaultsHelpFormatter)
@@ -194,7 +293,7 @@ def main():
     parser.add_argument('--json_input_dir', help='input annotated directory')
     parser.add_argument('--image_input_dir', help='image directory')
     parser.add_argument(
-        '--output_dir', help='output dataset directory', default='../../../')
+        '--output_dir', help='output dataset directory', default='./')
     parser.add_argument(
         '--train_proportion',
         help='the proportion of train dataset',
@@ -210,96 +309,137 @@ def main():
         help='the proportion of test dataset',
         type=float,
         default=0.0)
+    parser.add_argument(
+        '--voc_anno_dir',
+        help='In Voc format dataset, path to annotation files directory.',
+        type=str,
+        default=None)
+    parser.add_argument(
+        '--voc_anno_list',
+        help='In Voc format dataset, path to annotation files ids list.',
+        type=str,
+        default=None)
+    parser.add_argument(
+        '--voc_label_list',
+        help='In Voc format dataset, path to label list. The content of each line is a category.',
+        type=str,
+        default=None)
+    parser.add_argument(
+        '--voc_out_name',
+        type=str,
+        default='voc.json',
+        help='In Voc format dataset, path to output json file')
     args = parser.parse_args()
     try:
-        assert args.dataset_type in ['labelme', 'cityscape']
-    except AssertionError as e:
-        print('Now only support the cityscape dataset and labelme dataset!!')
-        os._exit(0)
-    try:
-        assert os.path.exists(args.json_input_dir)
-    except AssertionError as e:
-        print('The json folder does not exist!')
-        os._exit(0)
-    try:
-        assert os.path.exists(args.image_input_dir)
-    except AssertionError as e:
-        print('The image folder does not exist!')
-        os._exit(0)
-    try:
-        assert abs(args.train_proportion + args.val_proportion \
-                   + args.test_proportion - 1.0) < 1e-5
+        assert args.dataset_type in ['voc', 'labelme', 'cityscape']
     except AssertionError as e:
         print(
-            'The sum of pqoportion of training, validation and test datase must be 1!'
-        )
+            'Now only support the voc, cityscape dataset and labelme dataset!!')
         os._exit(0)
 
-    # Allocate the dataset.
-    total_num = len(glob.glob(osp.join(args.json_input_dir, '*.json')))
-    if args.train_proportion != 0:
-        train_num = int(total_num * args.train_proportion)
-        os.makedirs(args.output_dir + '/train')
+    if args.dataset_type == 'voc':
+        assert args.voc_anno_dir and args.voc_anno_list and args.voc_label_list
+        label2id, ann_paths = voc_get_label_anno(
+            args.voc_anno_dir, args.voc_anno_list, args.voc_label_list)
+        voc_xmls_to_cocojson(
+            annotation_paths=ann_paths,
+            label2id=label2id,
+            output_dir=args.output_dir,
+            output_file=args.voc_out_name)
     else:
-        train_num = 0
-    if args.val_proportion == 0.0:
-        val_num = 0
-        test_num = total_num - train_num
-        if args.test_proportion != 0.0:
-            os.makedirs(args.output_dir + '/test')
-    else:
-        val_num = int(total_num * args.val_proportion)
-        test_num = total_num - train_num - val_num
-        os.makedirs(args.output_dir + '/val')
-        if args.test_proportion != 0.0:
-            os.makedirs(args.output_dir + '/test')
-    count = 1
-    for img_name in os.listdir(args.image_input_dir):
-        if count <= train_num:
-            if osp.exists(args.output_dir + '/train/'):
-                shutil.copyfile(
-                    osp.join(args.image_input_dir, img_name),
-                    osp.join(args.output_dir + '/train/', img_name))
+        try:
+            assert os.path.exists(args.json_input_dir)
+        except AssertionError as e:
+            print('The json folder does not exist!')
+            os._exit(0)
+        try:
+            assert os.path.exists(args.image_input_dir)
+        except AssertionError as e:
+            print('The image folder does not exist!')
+            os._exit(0)
+        try:
+            assert abs(args.train_proportion + args.val_proportion \
+                    + args.test_proportion - 1.0) < 1e-5
+        except AssertionError as e:
+            print(
+                'The sum of pqoportion of training, validation and test datase must be 1!'
+            )
+            os._exit(0)
+
+        # Allocate the dataset.
+        total_num = len(glob.glob(osp.join(args.json_input_dir, '*.json')))
+        if args.train_proportion != 0:
+            train_num = int(total_num * args.train_proportion)
+            os.makedirs(args.output_dir + '/train')
         else:
-            if count <= train_num + val_num:
-                if osp.exists(args.output_dir + '/val/'):
+            train_num = 0
+        if args.val_proportion == 0.0:
+            val_num = 0
+            test_num = total_num - train_num
+            if args.test_proportion != 0.0:
+                os.makedirs(args.output_dir + '/test')
+        else:
+            val_num = int(total_num * args.val_proportion)
+            test_num = total_num - train_num - val_num
+            os.makedirs(args.output_dir + '/val')
+            if args.test_proportion != 0.0:
+                os.makedirs(args.output_dir + '/test')
+        count = 1
+        for img_name in os.listdir(args.image_input_dir):
+            if count <= train_num:
+                if osp.exists(args.output_dir + '/train/'):
                     shutil.copyfile(
                         osp.join(args.image_input_dir, img_name),
-                        osp.join(args.output_dir + '/val/', img_name))
+                        osp.join(args.output_dir + '/train/', img_name))
             else:
-                if osp.exists(args.output_dir + '/test/'):
-                    shutil.copyfile(
-                        osp.join(args.image_input_dir, img_name),
-                        osp.join(args.output_dir + '/test/', img_name))
-        count = count + 1
-
-    # Deal with the json files.
-    if not os.path.exists(args.output_dir + '/annotations'):
-        os.makedirs(args.output_dir + '/annotations')
-    if args.train_proportion != 0:
-        train_data_coco = deal_json(
-            args.dataset_type, args.output_dir + '/train', args.json_input_dir)
-        train_json_path = osp.join(args.output_dir + '/annotations',
-                                   'instance_train.json')
-        json.dump(
-            train_data_coco,
-            open(train_json_path, 'w'),
-            indent=4,
-            cls=MyEncoder)
-    if args.val_proportion != 0:
-        val_data_coco = deal_json(args.dataset_type, args.output_dir + '/val',
-                                  args.json_input_dir)
-        val_json_path = osp.join(args.output_dir + '/annotations',
-                                 'instance_val.json')
-        json.dump(
-            val_data_coco, open(val_json_path, 'w'), indent=4, cls=MyEncoder)
-    if args.test_proportion != 0:
-        test_data_coco = deal_json(args.dataset_type, args.output_dir + '/test',
-                                   args.json_input_dir)
-        test_json_path = osp.join(args.output_dir + '/annotations',
-                                  'instance_test.json')
-        json.dump(
-            test_data_coco, open(test_json_path, 'w'), indent=4, cls=MyEncoder)
+                if count <= train_num + val_num:
+                    if osp.exists(args.output_dir + '/val/'):
+                        shutil.copyfile(
+                            osp.join(args.image_input_dir, img_name),
+                            osp.join(args.output_dir + '/val/', img_name))
+                else:
+                    if osp.exists(args.output_dir + '/test/'):
+                        shutil.copyfile(
+                            osp.join(args.image_input_dir, img_name),
+                            osp.join(args.output_dir + '/test/', img_name))
+            count = count + 1
+
+        # Deal with the json files.
+        if not os.path.exists(args.output_dir + '/annotations'):
+            os.makedirs(args.output_dir + '/annotations')
+        if args.train_proportion != 0:
+            train_data_coco = deal_json(args.dataset_type,
+                                        args.output_dir + '/train',
+                                        args.json_input_dir)
+            train_json_path = osp.join(args.output_dir + '/annotations',
+                                       'instance_train.json')
+            json.dump(
+                train_data_coco,
+                open(train_json_path, 'w'),
+                indent=4,
+                cls=MyEncoder)
+        if args.val_proportion != 0:
+            val_data_coco = deal_json(args.dataset_type,
+                                      args.output_dir + '/val',
+                                      args.json_input_dir)
+            val_json_path = osp.join(args.output_dir + '/annotations',
+                                     'instance_val.json')
+            json.dump(
+                val_data_coco,
+                open(val_json_path, 'w'),
+                indent=4,
+                cls=MyEncoder)
+        if args.test_proportion != 0:
+            test_data_coco = deal_json(args.dataset_type,
+                                       args.output_dir + '/test',
+                                       args.json_input_dir)
+            test_json_path = osp.join(args.output_dir + '/annotations',
+                                      'instance_test.json')
+            json.dump(
+                test_data_coco,
+                open(test_json_path, 'w'),
+                indent=4,
+                cls=MyEncoder)
 
 
 if __name__ == '__main__':