Add xml dataset check (#4555)

* add a abvious import

* add a assert for CLASSES in XMLDataset

* change to get

* add voc tiny dataset

* add tiny voc

* add voc init test

* change to smalle iamge

* add xmlsubclass check

* add smaller image

* add comment for assert

mmdet/datasets/xml_style.py

@@ -20,6 +20,8 @@ class XMLDataset(CustomDataset):
     """
 
     def __init__(self, min_size=None, **kwargs):
+        assert self.CLASSES or kwargs.get(
+            'classes', None), 'CLASSES in `XMLDataset` can not be None.'
         super(XMLDataset, self).__init__(**kwargs)
         self.cat2label = {cat: i for i, cat in enumerate(self.CLASSES)}
         self.min_size = min_size
@@ -43,8 +45,6 @@ class XMLDataset(CustomDataset):
             tree = ET.parse(xml_path)
             root = tree.getroot()
             size = root.find('size')
-            width = 0
-            height = 0
             if size is not None:
                 width = int(size.find('width').text)
                 height = int(size.find('height').text)

tests/data/VOCdevkit/VOC2007/Annotations/000001.xml

+<annotation>
+	<folder>VOC2007</folder>
+	<filename>000001.jpg</filename>
+	<source>
+		<database>The VOC2007 Database</database>
+		<annotation>PASCAL VOC2007</annotation>
+		<image>flickr</image>
+		<flickrid>341012865</flickrid>
+	</source>
+	<owner>
+		<flickrid>Fried Camels</flickrid>
+		<name>Jinky the Fruit Bat</name>
+	</owner>
+	<size>
+		<width>353</width>
+		<height>500</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>dog</name>
+		<pose>Left</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>48</xmin>
+			<ymin>240</ymin>
+			<xmax>195</xmax>
+			<ymax>371</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>person</name>
+		<pose>Left</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>8</xmin>
+			<ymin>12</ymin>
+			<xmax>352</xmax>
+			<ymax>498</ymax>
+		</bndbox>
+	</object>
+</annotation>

tests/data/VOCdevkit/VOC2007/ImageSets/Main/test.txt

+000001

tests/data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt

+000001

tests/data/VOCdevkit/VOC2012/Annotations/000001.xml

+<annotation>
+	<folder>VOC2007</folder>
+	<filename>000002.jpg</filename>
+	<source>
+		<database>The VOC2007 Database</database>
+		<annotation>PASCAL VOC2007</annotation>
+		<image>flickr</image>
+		<flickrid>329145082</flickrid>
+	</source>
+	<owner>
+		<flickrid>hiromori2</flickrid>
+		<name>Hiroyuki Mori</name>
+	</owner>
+	<size>
+		<width>335</width>
+		<height>500</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>train</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>139</xmin>
+			<ymin>200</ymin>
+			<xmax>207</xmax>
+			<ymax>301</ymax>
+		</bndbox>
+	</object>
+</annotation>

tests/data/VOCdevkit/VOC2012/ImageSets/Main/test.txt

+000001

tests/data/VOCdevkit/VOC2012/ImageSets/Main/trainval.txt

+000001

tests/test_data/test_dataset.py

 import bisect
+import copy
 import logging
 import math
+import os
 import os.path as osp
 import tempfile
 from collections import defaultdict
@@ -104,6 +106,41 @@ def _create_dummy_results():
     return [boxes]
 
 
+def test_xml_dataset():
+    dataconfig = {
+        'ann_file': 'data/VOCdevkit/VOC2007/ImageSets/Main/test.txt',
+        'img_prefix': 'data/VOCdevkit/VOC2007/',
+        'pipeline': [{
+            'type': 'LoadImageFromFile'
+        }]
+    }
+    XMLDataset = DATASETS.get('XMLDataset')
+
+    class XMLDatasetSubClass(XMLDataset):
+        CLASSES = None
+
+    # get_ann_info and _filter_imgs of XMLDataset
+    # would use self.CLASSES, we added CLASSES not NONE
+    with pytest.raises(AssertionError):
+        XMLDatasetSubClass(**dataconfig)
+
+
+@pytest.mark.parametrize('config_path',
+                         ['./configs/_base_/datasets/voc0712.py'])
+def test_dataset_init(config_path):
+    if not os.path.exists('./data'):
+        os.symlink('./tests/data', './data')
+    data_config = mmcv.Config.fromfile(config_path)
+    if 'data' not in data_config:
+        return
+    stage_names = ['train', 'val', 'test']
+    for stage_name in stage_names:
+        dataset_config = copy.deepcopy(data_config.data.get(stage_name))
+        dataset = build_dataset(dataset_config)
+        dataset[0]
+    os.unlink('./data')
+
+
 def test_dataset_evaluation():
     tmp_dir = tempfile.TemporaryDirectory()
     # create dummy data