[Refactor]: Refactor unit test file structures (#4600)

* Refactor unittest

* Fix unittest

* Fix unittest

* Replace util with mmcv testing

* Try to reduce the unit test memory

tests/test_data/test_dataset.py → tests/test_data/test_datasets/test_common.py

-import bisect
 import copy
 import logging
-import math
 import os
 import os.path as osp
 import tempfile
-from collections import defaultdict
 from unittest.mock import MagicMock, patch
 
 import mmcv
@@ -17,9 +14,7 @@ from mmcv.runner import EpochBasedRunner
 from torch.utils.data import DataLoader
 
 from mmdet.core.evaluation import DistEvalHook, EvalHook
-from mmdet.datasets import (DATASETS, ClassBalancedDataset, CocoDataset,
-                            ConcatDataset, CustomDataset, RepeatDataset,
-                            build_dataset)
+from mmdet.datasets import DATASETS, CocoDataset, CustomDataset, build_dataset
 
 
 def _create_dummy_coco_json(json_name):
@@ -106,25 +101,6 @@ 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):
@@ -241,155 +217,6 @@ def test_dataset_evaluation():
     tmp_dir.cleanup()
 
 
-@patch('mmdet.datasets.CocoDataset.load_annotations', MagicMock)
-@patch('mmdet.datasets.CustomDataset.load_annotations', MagicMock)
-@patch('mmdet.datasets.XMLDataset.load_annotations', MagicMock)
-@patch('mmdet.datasets.CityscapesDataset.load_annotations', MagicMock)
-@patch('mmdet.datasets.CocoDataset._filter_imgs', MagicMock)
-@patch('mmdet.datasets.CustomDataset._filter_imgs', MagicMock)
-@patch('mmdet.datasets.XMLDataset._filter_imgs', MagicMock)
-@patch('mmdet.datasets.CityscapesDataset._filter_imgs', MagicMock)
-@pytest.mark.parametrize('dataset',
-                         ['CocoDataset', 'VOCDataset', 'CityscapesDataset'])
-def test_custom_classes_override_default(dataset):
-    dataset_class = DATASETS.get(dataset)
-    if dataset in ['CocoDataset', 'CityscapesDataset']:
-        dataset_class.coco = MagicMock()
-        dataset_class.cat_ids = MagicMock()
-
-    original_classes = dataset_class.CLASSES
-
-    # Test setting classes as a tuple
-    custom_dataset = dataset_class(
-        ann_file=MagicMock(),
-        pipeline=[],
-        classes=('bus', 'car'),
-        test_mode=True,
-        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
-
-    assert custom_dataset.CLASSES != original_classes
-    assert custom_dataset.CLASSES == ('bus', 'car')
-
-    # Test setting classes as a list
-    custom_dataset = dataset_class(
-        ann_file=MagicMock(),
-        pipeline=[],
-        classes=['bus', 'car'],
-        test_mode=True,
-        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
-
-    assert custom_dataset.CLASSES != original_classes
-    assert custom_dataset.CLASSES == ['bus', 'car']
-
-    # Test overriding not a subset
-    custom_dataset = dataset_class(
-        ann_file=MagicMock(),
-        pipeline=[],
-        classes=['foo'],
-        test_mode=True,
-        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
-
-    assert custom_dataset.CLASSES != original_classes
-    assert custom_dataset.CLASSES == ['foo']
-
-    # Test default behavior
-    custom_dataset = dataset_class(
-        ann_file=MagicMock(),
-        pipeline=[],
-        classes=None,
-        test_mode=True,
-        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
-
-    assert custom_dataset.CLASSES == original_classes
-
-    # Test sending file path
-    import tempfile
-    tmp_file = tempfile.NamedTemporaryFile()
-    with open(tmp_file.name, 'w') as f:
-        f.write('bus\ncar\n')
-    custom_dataset = dataset_class(
-        ann_file=MagicMock(),
-        pipeline=[],
-        classes=tmp_file.name,
-        test_mode=True,
-        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
-    tmp_file.close()
-
-    assert custom_dataset.CLASSES != original_classes
-    assert custom_dataset.CLASSES == ['bus', 'car']
-
-
-def test_dataset_wrapper():
-    CustomDataset.load_annotations = MagicMock()
-    CustomDataset.__getitem__ = MagicMock(side_effect=lambda idx: idx)
-    dataset_a = CustomDataset(
-        ann_file=MagicMock(), pipeline=[], test_mode=True, img_prefix='')
-    len_a = 10
-    cat_ids_list_a = [
-        np.random.randint(0, 80, num).tolist()
-        for num in np.random.randint(1, 20, len_a)
-    ]
-    dataset_a.data_infos = MagicMock()
-    dataset_a.data_infos.__len__.return_value = len_a
-    dataset_a.get_cat_ids = MagicMock(
-        side_effect=lambda idx: cat_ids_list_a[idx])
-    dataset_b = CustomDataset(
-        ann_file=MagicMock(), pipeline=[], test_mode=True, img_prefix='')
-    len_b = 20
-    cat_ids_list_b = [
-        np.random.randint(0, 80, num).tolist()
-        for num in np.random.randint(1, 20, len_b)
-    ]
-    dataset_b.data_infos = MagicMock()
-    dataset_b.data_infos.__len__.return_value = len_b
-    dataset_b.get_cat_ids = MagicMock(
-        side_effect=lambda idx: cat_ids_list_b[idx])
-
-    concat_dataset = ConcatDataset([dataset_a, dataset_b])
-    assert concat_dataset[5] == 5
-    assert concat_dataset[25] == 15
-    assert concat_dataset.get_cat_ids(5) == cat_ids_list_a[5]
-    assert concat_dataset.get_cat_ids(25) == cat_ids_list_b[15]
-    assert len(concat_dataset) == len(dataset_a) + len(dataset_b)
-
-    repeat_dataset = RepeatDataset(dataset_a, 10)
-    assert repeat_dataset[5] == 5
-    assert repeat_dataset[15] == 5
-    assert repeat_dataset[27] == 7
-    assert repeat_dataset.get_cat_ids(5) == cat_ids_list_a[5]
-    assert repeat_dataset.get_cat_ids(15) == cat_ids_list_a[5]
-    assert repeat_dataset.get_cat_ids(27) == cat_ids_list_a[7]
-    assert len(repeat_dataset) == 10 * len(dataset_a)
-
-    category_freq = defaultdict(int)
-    for cat_ids in cat_ids_list_a:
-        cat_ids = set(cat_ids)
-        for cat_id in cat_ids:
-            category_freq[cat_id] += 1
-    for k, v in category_freq.items():
-        category_freq[k] = v / len(cat_ids_list_a)
-
-    mean_freq = np.mean(list(category_freq.values()))
-    repeat_thr = mean_freq
-
-    category_repeat = {
-        cat_id: max(1.0, math.sqrt(repeat_thr / cat_freq))
-        for cat_id, cat_freq in category_freq.items()
-    }
-
-    repeat_factors = []
-    for cat_ids in cat_ids_list_a:
-        cat_ids = set(cat_ids)
-        repeat_factor = max({category_repeat[cat_id] for cat_id in cat_ids})
-        repeat_factors.append(math.ceil(repeat_factor))
-    repeat_factors_cumsum = np.cumsum(repeat_factors)
-    repeat_factor_dataset = ClassBalancedDataset(dataset_a, repeat_thr)
-    assert len(repeat_factor_dataset) == repeat_factors_cumsum[-1]
-    for idx in np.random.randint(0, len(repeat_factor_dataset), 3):
-        assert repeat_factor_dataset[idx] == bisect.bisect_right(
-            repeat_factors_cumsum, idx)
-
-
 @patch('mmdet.apis.single_gpu_test', MagicMock)
 @patch('mmdet.apis.multi_gpu_test', MagicMock)
 @pytest.mark.parametrize('EvalHookParam', (EvalHook, DistEvalHook))

tests/test_data/test_datasets/test_custom_dataset.py

+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from mmdet.datasets import DATASETS
+
+
+@patch('mmdet.datasets.CocoDataset.load_annotations', MagicMock)
+@patch('mmdet.datasets.CustomDataset.load_annotations', MagicMock)
+@patch('mmdet.datasets.XMLDataset.load_annotations', MagicMock)
+@patch('mmdet.datasets.CityscapesDataset.load_annotations', MagicMock)
+@patch('mmdet.datasets.CocoDataset._filter_imgs', MagicMock)
+@patch('mmdet.datasets.CustomDataset._filter_imgs', MagicMock)
+@patch('mmdet.datasets.XMLDataset._filter_imgs', MagicMock)
+@patch('mmdet.datasets.CityscapesDataset._filter_imgs', MagicMock)
+@pytest.mark.parametrize('dataset',
+                         ['CocoDataset', 'VOCDataset', 'CityscapesDataset'])
+def test_custom_classes_override_default(dataset):
+    dataset_class = DATASETS.get(dataset)
+    if dataset in ['CocoDataset', 'CityscapesDataset']:
+        dataset_class.coco = MagicMock()
+        dataset_class.cat_ids = MagicMock()
+
+    original_classes = dataset_class.CLASSES
+
+    # Test setting classes as a tuple
+    custom_dataset = dataset_class(
+        ann_file=MagicMock(),
+        pipeline=[],
+        classes=('bus', 'car'),
+        test_mode=True,
+        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
+
+    assert custom_dataset.CLASSES != original_classes
+    assert custom_dataset.CLASSES == ('bus', 'car')
+
+    # Test setting classes as a list
+    custom_dataset = dataset_class(
+        ann_file=MagicMock(),
+        pipeline=[],
+        classes=['bus', 'car'],
+        test_mode=True,
+        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
+
+    assert custom_dataset.CLASSES != original_classes
+    assert custom_dataset.CLASSES == ['bus', 'car']
+
+    # Test overriding not a subset
+    custom_dataset = dataset_class(
+        ann_file=MagicMock(),
+        pipeline=[],
+        classes=['foo'],
+        test_mode=True,
+        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
+
+    assert custom_dataset.CLASSES != original_classes
+    assert custom_dataset.CLASSES == ['foo']
+
+    # Test default behavior
+    custom_dataset = dataset_class(
+        ann_file=MagicMock(),
+        pipeline=[],
+        classes=None,
+        test_mode=True,
+        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
+
+    assert custom_dataset.CLASSES == original_classes
+
+    # Test sending file path
+    import tempfile
+    tmp_file = tempfile.NamedTemporaryFile()
+    with open(tmp_file.name, 'w') as f:
+        f.write('bus\ncar\n')
+    custom_dataset = dataset_class(
+        ann_file=MagicMock(),
+        pipeline=[],
+        classes=tmp_file.name,
+        test_mode=True,
+        img_prefix='VOC2007' if dataset == 'VOCDataset' else '')
+    tmp_file.close()
+
+    assert custom_dataset.CLASSES != original_classes
+    assert custom_dataset.CLASSES == ['bus', 'car']

tests/test_data/test_datasets/test_dataset_wrapper.py

+import bisect
+import math
+from collections import defaultdict
+from unittest.mock import MagicMock
+
+import numpy as np
+
+from mmdet.datasets import (ClassBalancedDataset, ConcatDataset, CustomDataset,
+                            RepeatDataset)
+
+
+def test_dataset_wrapper():
+    CustomDataset.load_annotations = MagicMock()
+    CustomDataset.__getitem__ = MagicMock(side_effect=lambda idx: idx)
+    dataset_a = CustomDataset(
+        ann_file=MagicMock(), pipeline=[], test_mode=True, img_prefix='')
+    len_a = 10
+    cat_ids_list_a = [
+        np.random.randint(0, 80, num).tolist()
+        for num in np.random.randint(1, 20, len_a)
+    ]
+    dataset_a.data_infos = MagicMock()
+    dataset_a.data_infos.__len__.return_value = len_a
+    dataset_a.get_cat_ids = MagicMock(
+        side_effect=lambda idx: cat_ids_list_a[idx])
+    dataset_b = CustomDataset(
+        ann_file=MagicMock(), pipeline=[], test_mode=True, img_prefix='')
+    len_b = 20
+    cat_ids_list_b = [
+        np.random.randint(0, 80, num).tolist()
+        for num in np.random.randint(1, 20, len_b)
+    ]
+    dataset_b.data_infos = MagicMock()
+    dataset_b.data_infos.__len__.return_value = len_b
+    dataset_b.get_cat_ids = MagicMock(
+        side_effect=lambda idx: cat_ids_list_b[idx])
+
+    concat_dataset = ConcatDataset([dataset_a, dataset_b])
+    assert concat_dataset[5] == 5
+    assert concat_dataset[25] == 15
+    assert concat_dataset.get_cat_ids(5) == cat_ids_list_a[5]
+    assert concat_dataset.get_cat_ids(25) == cat_ids_list_b[15]
+    assert len(concat_dataset) == len(dataset_a) + len(dataset_b)
+
+    repeat_dataset = RepeatDataset(dataset_a, 10)
+    assert repeat_dataset[5] == 5
+    assert repeat_dataset[15] == 5
+    assert repeat_dataset[27] == 7
+    assert repeat_dataset.get_cat_ids(5) == cat_ids_list_a[5]
+    assert repeat_dataset.get_cat_ids(15) == cat_ids_list_a[5]
+    assert repeat_dataset.get_cat_ids(27) == cat_ids_list_a[7]
+    assert len(repeat_dataset) == 10 * len(dataset_a)
+
+    category_freq = defaultdict(int)
+    for cat_ids in cat_ids_list_a:
+        cat_ids = set(cat_ids)
+        for cat_id in cat_ids:
+            category_freq[cat_id] += 1
+    for k, v in category_freq.items():
+        category_freq[k] = v / len(cat_ids_list_a)
+
+    mean_freq = np.mean(list(category_freq.values()))
+    repeat_thr = mean_freq
+
+    category_repeat = {
+        cat_id: max(1.0, math.sqrt(repeat_thr / cat_freq))
+        for cat_id, cat_freq in category_freq.items()
+    }
+
+    repeat_factors = []
+    for cat_ids in cat_ids_list_a:
+        cat_ids = set(cat_ids)
+        repeat_factor = max({category_repeat[cat_id] for cat_id in cat_ids})
+        repeat_factors.append(math.ceil(repeat_factor))
+    repeat_factors_cumsum = np.cumsum(repeat_factors)
+    repeat_factor_dataset = ClassBalancedDataset(dataset_a, repeat_thr)
+    assert len(repeat_factor_dataset) == repeat_factors_cumsum[-1]
+    for idx in np.random.randint(0, len(repeat_factor_dataset), 3):
+        assert repeat_factor_dataset[idx] == bisect.bisect_right(
+            repeat_factors_cumsum, idx)

tests/test_data/test_datasets/test_xml_dataset.py

+import pytest
+
+from mmdet.datasets import DATASETS
+
+
+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)

tests/test_data/test_formatting.py → tests/test_data/test_pipelines/test_formatting.py

@@ -7,7 +7,7 @@ from mmdet.datasets.builder import PIPELINES
 
 def test_default_format_bundle():
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../data'),
         img_info=dict(filename='color.jpg'))
     load = dict(type='LoadImageFromFile')
     load = build_from_cfg(load, PIPELINES)

tests/test_data/test_loading.py → tests/test_data/test_pipelines/test_loading.py

@@ -12,7 +12,7 @@ class TestLoading(object):
 
     @classmethod
     def setup_class(cls):
-        cls.data_prefix = osp.join(osp.dirname(__file__), '../data')
+        cls.data_prefix = osp.join(osp.dirname(__file__), '../../data')
 
     def test_load_img(self):
         results = dict(

tests/test_data/test_models_aug_test.py → tests/test_data/test_pipelines/test_transform/test_models_aug_test.py

@@ -26,7 +26,7 @@ def model_aug_test_template(cfg_file):
     transform = build_from_cfg(multi_scale_cfg, PIPELINES)
 
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
     results = transform(load(results))
     assert len(results['img']) == 6
@@ -43,7 +43,7 @@ def model_aug_test_template(cfg_file):
 
 def test_aug_test_size():
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
 
     # Define simple pipeline
@@ -113,7 +113,7 @@ def test_cornernet_aug_test():
     transform = build_from_cfg(multi_scale_cfg, PIPELINES)
 
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
     results = transform(load(results))
     assert len(results['img']) == 6

tests/test_data/test_transform.py → tests/test_data/test_pipelines/test_transform/test_transform.py

@@ -38,7 +38,7 @@ def test_resize():
     # test assertion if both scale and scale_factor are setted
     with pytest.raises(AssertionError):
         results = dict(
-            img_prefix=osp.join(osp.dirname(__file__), '../data'),
+            img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
             img_info=dict(filename='color.jpg'))
         load = dict(type='LoadImageFromFile')
         load = build_from_cfg(load, PIPELINES)
@@ -54,7 +54,7 @@ def test_resize():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     results['img'] = img
     results['img2'] = copy.deepcopy(img)
     results['img_shape'] = img.shape
@@ -108,7 +108,7 @@ def test_flip():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     original_img = copy.deepcopy(img)
     results['img'] = img
     results['img2'] = copy.deepcopy(img)
@@ -136,7 +136,7 @@ def test_flip():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     original_img = copy.deepcopy(img)
     results['img'] = img
     results['img_shape'] = img.shape
@@ -162,7 +162,7 @@ def test_flip():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     original_img = copy.deepcopy(img)
     results['img'] = img
     results['img_shape'] = img.shape
@@ -188,7 +188,7 @@ def test_random_crop():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     results['img'] = img
 
     results['img_shape'] = img.shape
@@ -315,7 +315,7 @@ def test_min_iou_random_crop():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     results['img'] = img
 
     results['img_shape'] = img.shape
@@ -363,7 +363,7 @@ def test_pad():
     transform = build_from_cfg(transform, PIPELINES)
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     original_img = copy.deepcopy(img)
     results['img'] = img
     results['img2'] = copy.deepcopy(img)
@@ -402,7 +402,7 @@ def test_normalize():
     transform = build_from_cfg(transform, PIPELINES)
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     original_img = copy.deepcopy(img)
     results['img'] = img
     results['img2'] = copy.deepcopy(img)
@@ -424,7 +424,7 @@ def test_normalize():
 
 def test_albu_transform():
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
 
     # Define simple pipeline
@@ -535,7 +535,7 @@ def test_random_center_crop_pad():
         build_from_cfg(transform, PIPELINES)
 
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
 
     load = dict(type='LoadImageFromFile', to_float32=True)
@@ -636,7 +636,7 @@ def test_multi_scale_flip_aug():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
     results['img'] = img
     results['img_shape'] = img.shape
     results['ori_shape'] = img.shape
@@ -667,7 +667,7 @@ def test_multi_scale_flip_aug():
 
     # test pipeline of coco_detection
     results = dict(
-        img_prefix=osp.join(osp.dirname(__file__), '../data'),
+        img_prefix=osp.join(osp.dirname(__file__), '../../../data'),
         img_info=dict(filename='color.jpg'))
     load_cfg, multi_scale_cfg = mmcv.Config.fromfile(
         'configs/_base_/datasets/coco_detection.py').test_pipeline
@@ -715,7 +715,7 @@ def test_cutout():
 
     results = dict()
     img = mmcv.imread(
-        osp.join(osp.dirname(__file__), '../data/color.jpg'), 'color')
+        osp.join(osp.dirname(__file__), '../../../data/color.jpg'), 'color')
 
     results['img'] = img
     results['img_shape'] = img.shape

tests/test_models/test_backbones/__init__.py

+from .utils import check_norm_state, is_block, is_norm
+
+__all__ = ['is_block', 'is_norm', 'check_norm_state']

tests/test_models/test_backbones/test_hourglass.py

+import pytest
+import torch
+
+from mmdet.models.backbones.hourglass import HourglassNet
+
+
+def test_hourglass_backbone():
+    with pytest.raises(AssertionError):
+        # HourglassNet's num_stacks should larger than 0
+        HourglassNet(num_stacks=0)
+
+    with pytest.raises(AssertionError):
+        # len(stage_channels) should equal len(stage_blocks)
+        HourglassNet(
+            stage_channels=[256, 256, 384, 384, 384],
+            stage_blocks=[2, 2, 2, 2, 2, 4])
+
+    with pytest.raises(AssertionError):
+        # len(stage_channels) should lagrer than downsample_times
+        HourglassNet(
+            downsample_times=5,
+            stage_channels=[256, 256, 384, 384, 384],
+            stage_blocks=[2, 2, 2, 2, 2])
+
+    # Test HourglassNet-52
+    model = HourglassNet(num_stacks=1)
+    model.init_weights()
+    model.train()
+
+    imgs = torch.randn(1, 3, 256, 256)
+    feat = model(imgs)
+    assert len(feat) == 1
+    assert feat[0].shape == torch.Size([1, 256, 64, 64])
+
+    # Test HourglassNet-104
+    model = HourglassNet(num_stacks=2)
+    model.init_weights()
+    model.train()
+
+    imgs = torch.randn(1, 3, 256, 256)
+    feat = model(imgs)
+    assert len(feat) == 2
+    assert feat[0].shape == torch.Size([1, 256, 64, 64])
+    assert feat[1].shape == torch.Size([1, 256, 64, 64])

tests/test_models/test_backbones/test_regnet.py

+import pytest
+import torch
+
+from mmdet.models.backbones import RegNet
+
+regnet_test_data = [
+    ('regnetx_400mf',
+     dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22,
+          bot_mul=1.0), [32, 64, 160, 384]),
+    ('regnetx_800mf',
+     dict(w0=56, wa=35.73, wm=2.28, group_w=16, depth=16,
+          bot_mul=1.0), [64, 128, 288, 672]),
+    ('regnetx_1.6gf',
+     dict(w0=80, wa=34.01, wm=2.25, group_w=24, depth=18,
+          bot_mul=1.0), [72, 168, 408, 912]),
+    ('regnetx_3.2gf',
+     dict(w0=88, wa=26.31, wm=2.25, group_w=48, depth=25,
+          bot_mul=1.0), [96, 192, 432, 1008]),
+    ('regnetx_4.0gf',
+     dict(w0=96, wa=38.65, wm=2.43, group_w=40, depth=23,
+          bot_mul=1.0), [80, 240, 560, 1360]),
+    ('regnetx_6.4gf',
+     dict(w0=184, wa=60.83, wm=2.07, group_w=56, depth=17,
+          bot_mul=1.0), [168, 392, 784, 1624]),
+    ('regnetx_8.0gf',
+     dict(w0=80, wa=49.56, wm=2.88, group_w=120, depth=23,
+          bot_mul=1.0), [80, 240, 720, 1920]),
+    ('regnetx_12gf',
+     dict(w0=168, wa=73.36, wm=2.37, group_w=112, depth=19,
+          bot_mul=1.0), [224, 448, 896, 2240]),
+]
+
+
+@pytest.mark.parametrize('arch_name,arch,out_channels', regnet_test_data)
+def test_regnet_backbone(arch_name, arch, out_channels):
+    with pytest.raises(AssertionError):
+        # ResNeXt depth should be in [50, 101, 152]
+        RegNet(arch_name + '233')
+
+    # Test RegNet with arch_name
+    model = RegNet(arch_name)
+    model.init_weights()
+    model.train()
+
+    imgs = torch.randn(1, 3, 224, 224)
+    feat = model(imgs)
+    assert len(feat) == 4
+    assert feat[0].shape == torch.Size([1, out_channels[0], 56, 56])
+    assert feat[1].shape == torch.Size([1, out_channels[1], 28, 28])
+    assert feat[2].shape == torch.Size([1, out_channels[2], 14, 14])
+    assert feat[3].shape == torch.Size([1, out_channels[3], 7, 7])
+
+    # Test RegNet with arch
+    model = RegNet(arch)
+    assert feat[0].shape == torch.Size([1, out_channels[0], 56, 56])
+    assert feat[1].shape == torch.Size([1, out_channels[1], 28, 28])
+    assert feat[2].shape == torch.Size([1, out_channels[2], 14, 14])
+    assert feat[3].shape == torch.Size([1, out_channels[3], 7, 7])

tests/test_models/test_backbones/test_renext.py

+import pytest
+import torch
+
+from mmdet.models.backbones import ResNeXt
+from mmdet.models.backbones.resnext import Bottleneck as BottleneckX
+from .utils import is_block
+
+
+def test_renext_bottleneck():
+    with pytest.raises(AssertionError):
+        # Style must be in ['pytorch', 'caffe']
+        BottleneckX(64, 64, groups=32, base_width=4, style='tensorflow')
+
+    # Test ResNeXt Bottleneck structure
+    block = BottleneckX(
+        64, 64, groups=32, base_width=4, stride=2, style='pytorch')
+    assert block.conv2.stride == (2, 2)
+    assert block.conv2.groups == 32
+    assert block.conv2.out_channels == 128
+
+    # Test ResNeXt Bottleneck with DCN
+    dcn = dict(type='DCN', deform_groups=1, fallback_on_stride=False)
+    with pytest.raises(AssertionError):
+        # conv_cfg must be None if dcn is not None
+        BottleneckX(
+            64,
+            64,
+            groups=32,
+            base_width=4,
+            dcn=dcn,
+            conv_cfg=dict(type='Conv'))
+    BottleneckX(64, 64, dcn=dcn)
+
+    # Test ResNeXt Bottleneck forward
+    block = BottleneckX(64, 16, groups=32, base_width=4)
+    x = torch.randn(1, 64, 56, 56)
+    x_out = block(x)
+    assert x_out.shape == torch.Size([1, 64, 56, 56])
+
+    # Test ResNeXt Bottleneck forward with plugins
+    plugins = [
+        dict(
+            cfg=dict(
+                type='GeneralizedAttention',
+                spatial_range=-1,
+                num_heads=8,
+                attention_type='0010',
+                kv_stride=2),
+            stages=(False, False, True, True),
+            position='after_conv2')
+    ]
+    block = BottleneckX(64, 16, groups=32, base_width=4, plugins=plugins)
+    x = torch.randn(1, 64, 56, 56)
+    x_out = block(x)
+    assert x_out.shape == torch.Size([1, 64, 56, 56])
+
+
+def test_resnext_backbone():
+    with pytest.raises(KeyError):
+        # ResNeXt depth should be in [50, 101, 152]
+        ResNeXt(depth=18)
+
+    # Test ResNeXt with group 32, base_width 4
+    model = ResNeXt(depth=50, groups=32, base_width=4)
+    for m in model.modules():
+        if is_block(m):
+            assert m.conv2.groups == 32
+    model.init_weights()
+    model.train()
+
+    imgs = torch.randn(1, 3, 224, 224)
+    feat = model(imgs)
+    assert len(feat) == 4
+    assert feat[0].shape == torch.Size([1, 256, 56, 56])
+    assert feat[1].shape == torch.Size([1, 512, 28, 28])
+    assert feat[2].shape == torch.Size([1, 1024, 14, 14])
+    assert feat[3].shape == torch.Size([1, 2048, 7, 7])
+
+
+regnet_test_data = [
+    ('regnetx_400mf',
+     dict(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22,
+          bot_mul=1.0), [32, 64, 160, 384]),
+    ('regnetx_800mf',
+     dict(w0=56, wa=35.73, wm=2.28, group_w=16, depth=16,
+          bot_mul=1.0), [64, 128, 288, 672]),
+    ('regnetx_1.6gf',
+     dict(w0=80, wa=34.01, wm=2.25, group_w=24, depth=18,
+          bot_mul=1.0), [72, 168, 408, 912]),
+    ('regnetx_3.2gf',
+     dict(w0=88, wa=26.31, wm=2.25, group_w=48, depth=25,
+          bot_mul=1.0), [96, 192, 432, 1008]),
+    ('regnetx_4.0gf',
+     dict(w0=96, wa=38.65, wm=2.43, group_w=40, depth=23,
+          bot_mul=1.0), [80, 240, 560, 1360]),
+    ('regnetx_6.4gf',
+     dict(w0=184, wa=60.83, wm=2.07, group_w=56, depth=17,
+          bot_mul=1.0), [168, 392, 784, 1624]),
+    ('regnetx_8.0gf',
+     dict(w0=80, wa=49.56, wm=2.88, group_w=120, depth=23,
+          bot_mul=1.0), [80, 240, 720, 1920]),
+    ('regnetx_12gf',
+     dict(w0=168, wa=73.36, wm=2.37, group_w=112, depth=19,
+          bot_mul=1.0), [224, 448, 896, 2240]),
+]

tests/test_models/test_backbones/test_res2net.py

+import pytest
+import torch
+
+from mmdet.models.backbones import Res2Net
+from mmdet.models.backbones.res2net import Bottle2neck
+from .utils import is_block
+
+
+def test_res2net_bottle2neck():
+    with pytest.raises(AssertionError):
+        # Style must be in ['pytorch', 'caffe']
+        Bottle2neck(64, 64, base_width=26, scales=4, style='tensorflow')
+
+    with pytest.raises(AssertionError):
+        # Scale must be larger than 1
+        Bottle2neck(64, 64, base_width=26, scales=1, style='pytorch')
+
+    # Test Res2Net Bottle2neck structure
+    block = Bottle2neck(
+        64, 64, base_width=26, stride=2, scales=4, style='pytorch')
+    assert block.scales == 4
+
+    # Test Res2Net Bottle2neck with DCN
+    dcn = dict(type='DCN', deform_groups=1, fallback_on_stride=False)
+    with pytest.raises(AssertionError):
+        # conv_cfg must be None if dcn is not None
+        Bottle2neck(
+            64,
+            64,
+            base_width=26,
+            scales=4,
+            dcn=dcn,
+            conv_cfg=dict(type='Conv'))
+    Bottle2neck(64, 64, dcn=dcn)
+
+    # Test Res2Net Bottle2neck forward
+    block = Bottle2neck(64, 16, base_width=26, scales=4)
+    x = torch.randn(1, 64, 56, 56)
+    x_out = block(x)
+    assert x_out.shape == torch.Size([1, 64, 56, 56])
+
+
+def test_res2net_backbone():
+    with pytest.raises(KeyError):
+        # Res2Net depth should be in [50, 101, 152]
+        Res2Net(depth=18)
+
+    # Test Res2Net with scales 4, base_width 26
+    model = Res2Net(depth=50, scales=4, base_width=26)
+    for m in model.modules():
+        if is_block(m):
+            assert m.scales == 4
+    model.init_weights()
+    model.train()
+
+    imgs = torch.randn(1, 3, 224, 224)
+    feat = model(imgs)
+    assert len(feat) == 4
+    assert feat[0].shape == torch.Size([1, 256, 56, 56])
+    assert feat[1].shape == torch.Size([1, 512, 28, 28])
+    assert feat[2].shape == torch.Size([1, 1024, 14, 14])
+    assert feat[3].shape == torch.Size([1, 2048, 7, 7])