Fix miss text (#278)

* fixed the bug about miss text files on kitti testing

* add bbox2result_kitti unit test

* add bbox2result_kitti unit test

* add exist_submission_file unit test

* deleted debug code and convert{} to dict()

* add _get_kitti_dataset_config()

* delete print

mmdet3d/datasets/kitti_dataset.py

@@ -387,15 +387,7 @@ class KittiDataset(Custom3DDataset):
             info = self.data_infos[idx]
             sample_idx = info['image']['image_idx']
             image_shape = info['image']['image_shape'][:2]
-
             box_dict = self.convert_valid_bboxes(pred_dicts, info)
-            if len(box_dict['bbox']) > 0:
-                box_2d_preds = box_dict['bbox']
-                box_preds = box_dict['box3d_camera']
-                scores = box_dict['scores']
-                box_preds_lidar = box_dict['box3d_lidar']
-                label_preds = box_dict['label_preds']
-
             anno = {
                 'name': [],
                 'truncated': [],
@@ -407,6 +399,12 @@ class KittiDataset(Custom3DDataset):
                 'rotation_y': [],
                 'score': []
             }
+            if len(box_dict['bbox']) > 0:
+                box_2d_preds = box_dict['bbox']
+                box_preds = box_dict['box3d_camera']
+                scores = box_dict['scores']
+                box_preds_lidar = box_dict['box3d_lidar']
+                label_preds = box_dict['label_preds']
 
                 for box, box_lidar, bbox, score, label in zip(
                         box_preds, box_preds_lidar, box_2d_preds, scores,
@@ -426,6 +424,19 @@ class KittiDataset(Custom3DDataset):
 
                 anno = {k: np.stack(v) for k, v in anno.items()}
                 annos.append(anno)
+            else:
+                anno = {
+                    'name': np.array([]),
+                    'truncated': np.array([]),
+                    'occluded': np.array([]),
+                    'alpha': np.array([]),
+                    'bbox': np.zeros([0, 4]),
+                    'dimensions': np.zeros([0, 3]),
+                    'location': np.zeros([0, 3]),
+                    'rotation_y': np.array([]),
+                    'score': np.array([]),
+                }
+                annos.append(anno)
 
             if submission_prefix is not None:
                 curr_file = f'{submission_prefix}/{sample_idx:06d}.txt'
@@ -438,27 +449,15 @@ class KittiDataset(Custom3DDataset):
                         print(
                             '{} -1 -1 {:.4f} {:.4f} {:.4f} {:.4f} '
                             '{:.4f} {:.4f} {:.4f} '
-                                '{:.4f} {:.4f} {:.4f} {:.4f} {:.4f} {:.4f}'.
-                                format(anno['name'][idx], anno['alpha'][idx],
-                                       bbox[idx][0], bbox[idx][1],
-                                       bbox[idx][2], bbox[idx][3],
-                                       dims[idx][1], dims[idx][2],
+                            '{:.4f} {:.4f} {:.4f} {:.4f} {:.4f} {:.4f}'.format(
+                                anno['name'][idx], anno['alpha'][idx],
+                                bbox[idx][0], bbox[idx][1], bbox[idx][2],
+                                bbox[idx][3], dims[idx][1], dims[idx][2],
                                 dims[idx][0], loc[idx][0], loc[idx][1],
                                 loc[idx][2], anno['rotation_y'][idx],
                                 anno['score'][idx]),
                             file=f)
-            else:
-                annos.append({
-                    'name': np.array([]),
-                    'truncated': np.array([]),
-                    'occluded': np.array([]),
-                    'alpha': np.array([]),
-                    'bbox': np.zeros([0, 4]),
-                    'dimensions': np.zeros([0, 3]),
-                    'location': np.zeros([0, 3]),
-                    'rotation_y': np.array([]),
-                    'score': np.array([]),
-                })
+
             annos[-1]['sample_idx'] = np.array(
                 [sample_idx] * len(annos[-1]['score']), dtype=np.int64)
 

tests/test_dataset/test_kitti_dataset.py

 import numpy as np
+import os
 import pytest
+import tempfile
 import torch
 
 from mmdet3d.core.bbox import LiDARInstance3DBoxes
 from mmdet3d.datasets import KittiDataset
 
 
-def test_getitem():
-    np.random.seed(0)
+def _generate_kitti_dataset_config():
     data_root = 'tests/data/kitti'
     ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
     classes = ['Pedestrian', 'Cyclist', 'Car']
     pts_prefix = 'velodyne_reduced'
-    pipeline = [{
-        'type': 'LoadPointsFromFile',
-        'coord_type': 'LIDAR',
-        'load_dim': 4,
-        'use_dim': 4,
-        'file_client_args': {
-            'backend': 'disk'
-        }
-    }, {
-        'type': 'LoadAnnotations3D',
-        'with_bbox_3d': True,
-        'with_label_3d': True,
-        'file_client_args': {
-            'backend': 'disk'
-        }
-    }, {
-        'type': 'ObjectSample',
-        'db_sampler': {
-            'data_root': 'tests/data/kitti/',
-            'info_path': 'tests/data/kitti/kitti_dbinfos_train.pkl',
-            'rate': 1.0,
-            'prepare': {
-                'filter_by_difficulty': [-1],
-                'filter_by_min_points': {
-                    'Pedestrian': 10
-                }
-            },
-            'classes': ['Pedestrian', 'Cyclist', 'Car'],
-            'sample_groups': {
-                'Pedestrian': 6
-            }
-        }
-    }, {
-        'type': 'ObjectNoise',
-        'num_try': 100,
-        'translation_std': [1.0, 1.0, 0.5],
-        'global_rot_range': [0.0, 0.0],
-        'rot_range': [-0.78539816, 0.78539816]
-    }, {
-        'type': 'RandomFlip3D',
-        'flip_ratio_bev_horizontal': 0.5
-    }, {
-        'type': 'GlobalRotScaleTrans',
-        'rot_range': [-0.78539816, 0.78539816],
-        'scale_ratio_range': [0.95, 1.05]
-    }, {
-        'type': 'PointsRangeFilter',
-        'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
-    }, {
-        'type': 'ObjectRangeFilter',
-        'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
-    }, {
-        'type': 'PointShuffle'
-    }, {
-        'type': 'DefaultFormatBundle3D',
-        'class_names': ['Pedestrian', 'Cyclist', 'Car']
-    }, {
-        'type': 'Collect3D',
-        'keys': ['points', 'gt_bboxes_3d', 'gt_labels_3d']
-    }]
-    modality = {'use_lidar': True, 'use_camera': False}
+    pipeline = [
+        dict(
+            type='LoadPointsFromFile',
+            coord_type='LIDAR',
+            load_dim=4,
+            use_dim=4,
+            file_client_args=dict(backend='disk')),
+        dict(
+            type='MultiScaleFlipAug3D',
+            img_scale=(1333, 800),
+            pts_scale_ratio=1,
+            flip=False,
+            transforms=[
+                dict(
+                    type='GlobalRotScaleTrans',
+                    rot_range=[0, 0],
+                    scale_ratio_range=[1.0, 1.0],
+                    translation_std=[0, 0, 0]),
+                dict(type='RandomFlip3D'),
+                dict(
+                    type='PointsRangeFilter',
+                    point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
+                dict(
+                    type='DefaultFormatBundle3D',
+                    class_names=['Pedestrian', 'Cyclist', 'Car'],
+                    with_label=False),
+                dict(type='Collect3D', keys=['points'])
+            ])
+    ]
+    modality = dict(use_lidar=True, use_camera=False)
     split = 'training'
+    return data_root, ann_file, classes, pts_prefix, pipeline, modality, split
+
+
+def test_getitem():
+    np.random.seed(0)
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
+    pipeline = [
+        dict(
+            type='LoadPointsFromFile',
+            coord_type='LIDAR',
+            load_dim=4,
+            use_dim=4,
+            file_client_args=dict(backend='disk')),
+        dict(
+            type='LoadAnnotations3D',
+            with_bbox_3d=True,
+            with_label_3d=True,
+            file_client_args=dict(backend='disk')),
+        dict(
+            type='ObjectSample',
+            db_sampler=dict(
+                data_root='tests/data/kitti/',
+                info_path='tests/data/kitti/kitti_dbinfos_train.pkl',
+                rate=1.0,
+                prepare=dict(
+                    filter_by_difficulty=[-1],
+                    filter_by_min_points=dict(Pedestrian=10)),
+                classes=['Pedestrian', 'Cyclist', 'Car'],
+                sample_groups=dict(Pedestrian=6))),
+        dict(
+            type='ObjectNoise',
+            num_try=100,
+            translation_std=[1.0, 1.0, 0.5],
+            global_rot_range=[0.0, 0.0],
+            rot_range=[-0.78539816, 0.78539816]),
+        dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
+        dict(
+            type='GlobalRotScaleTrans',
+            rot_range=[-0.78539816, 0.78539816],
+            scale_ratio_range=[0.95, 1.05]),
+        dict(
+            type='PointsRangeFilter',
+            point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
+        dict(
+            type='ObjectRangeFilter',
+            point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
+        dict(type='PointShuffle'),
+        dict(
+            type='DefaultFormatBundle3D',
+            class_names=['Pedestrian', 'Cyclist', 'Car']),
+        dict(
+            type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
+    ]
     self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
                         classes, modality)
     data = self[0]
@@ -92,56 +116,10 @@ def test_getitem():
 def test_evaluate():
     if not torch.cuda.is_available():
         pytest.skip('test requires GPU and torch+cuda')
-    data_root = 'tests/data/kitti'
-    ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
-    classes = ['Pedestrian', 'Cyclist', 'Car']
-    pts_prefix = 'velodyne_reduced'
-    pipeline = [{
-        'type': 'LoadPointsFromFile',
-        'coord_type': 'LIDAR',
-        'load_dim': 4,
-        'use_dim': 4,
-        'file_client_args': {
-            'backend': 'disk'
-        }
-    }, {
-        'type':
-        'MultiScaleFlipAug3D',
-        'img_scale': (1333, 800),
-        'pts_scale_ratio':
-        1,
-        'flip':
-        False,
-        'transforms': [{
-            'type': 'GlobalRotScaleTrans',
-            'rot_range': [0, 0],
-            'scale_ratio_range': [1.0, 1.0],
-            'translation_std': [0, 0, 0]
-        }, {
-            'type': 'RandomFlip3D'
-        }, {
-            'type': 'PointsRangeFilter',
-            'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
-        }, {
-            'type': 'DefaultFormatBundle3D',
-            'class_names': ['Pedestrian', 'Cyclist', 'Car'],
-            'with_label': False
-        }, {
-            'type': 'Collect3D',
-            'keys': ['points']
-        }]
-    }]
-    modality = {'use_lidar': True, 'use_camera': False}
-    split = 'training'
-    self = KittiDataset(
-        data_root,
-        ann_file,
-        split,
-        pts_prefix,
-        pipeline,
-        classes,
-        modality,
-    )
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
+    self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
+                        classes, modality)
     boxes_3d = LiDARInstance3DBoxes(
         torch.tensor(
             [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
@@ -164,42 +142,8 @@ def test_show():
 
     from mmdet3d.core.bbox import LiDARInstance3DBoxes
     temp_dir = tempfile.mkdtemp()
-    data_root = 'tests/data/kitti'
-    ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
-    modality = {'use_lidar': True, 'use_camera': False}
-    split = 'training'
-    file_client_args = dict(backend='disk')
-    point_cloud_range = [0, -40, -3, 70.4, 40, 1]
-    class_names = ['Pedestrian', 'Cyclist', 'Car']
-    pipeline = [
-        dict(
-            type='LoadPointsFromFile',
-            coord_type='LIDAR',
-            load_dim=4,
-            use_dim=4,
-            file_client_args=file_client_args),
-        dict(
-            type='MultiScaleFlipAug3D',
-            img_scale=(1333, 800),
-            pts_scale_ratio=1,
-            flip=False,
-            transforms=[
-                dict(
-                    type='GlobalRotScaleTrans',
-                    rot_range=[0, 0],
-                    scale_ratio_range=[1., 1.],
-                    translation_std=[0, 0, 0]),
-                dict(type='RandomFlip3D'),
-                dict(
-                    type='PointsRangeFilter',
-                    point_cloud_range=point_cloud_range),
-                dict(
-                    type='DefaultFormatBundle3D',
-                    class_names=class_names,
-                    with_label=False),
-                dict(type='Collect3D', keys=['points'])
-            ])
-    ]
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
     kitti_dataset = KittiDataset(
         data_root, ann_file, split=split, modality=modality, pipeline=pipeline)
     boxes_3d = LiDARInstance3DBoxes(
@@ -224,56 +168,10 @@ def test_show():
 
 def test_format_results():
     from mmdet3d.core.bbox import LiDARInstance3DBoxes
-    data_root = 'tests/data/kitti'
-    ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
-    classes = ['Pedestrian', 'Cyclist', 'Car']
-    pts_prefix = 'velodyne_reduced'
-    pipeline = [{
-        'type': 'LoadPointsFromFile',
-        'coord_type': 'LIDAR',
-        'load_dim': 4,
-        'use_dim': 4,
-        'file_client_args': {
-            'backend': 'disk'
-        }
-    }, {
-        'type':
-        'MultiScaleFlipAug3D',
-        'img_scale': (1333, 800),
-        'pts_scale_ratio':
-        1,
-        'flip':
-        False,
-        'transforms': [{
-            'type': 'GlobalRotScaleTrans',
-            'rot_range': [0, 0],
-            'scale_ratio_range': [1.0, 1.0],
-            'translation_std': [0, 0, 0]
-        }, {
-            'type': 'RandomFlip3D'
-        }, {
-            'type': 'PointsRangeFilter',
-            'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
-        }, {
-            'type': 'DefaultFormatBundle3D',
-            'class_names': ['Pedestrian', 'Cyclist', 'Car'],
-            'with_label': False
-        }, {
-            'type': 'Collect3D',
-            'keys': ['points']
-        }]
-    }]
-    modality = {'use_lidar': True, 'use_camera': False}
-    split = 'training'
-    self = KittiDataset(
-        data_root,
-        ann_file,
-        split,
-        pts_prefix,
-        pipeline,
-        classes,
-        modality,
-    )
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
+    self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
+                        classes, modality)
     boxes_3d = LiDARInstance3DBoxes(
         torch.tensor(
             [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
@@ -306,57 +204,56 @@ def test_format_results():
     assert np.allclose(result_files[0]['sample_idx'], expected_sample_idx)
 
 
+def test_bbox2result_kitti():
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
+    self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
+                        classes, modality)
+    boxes_3d = LiDARInstance3DBoxes(
+        torch.tensor(
+            [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
+    labels_3d = torch.tensor([
+        0,
+    ])
+    scores_3d = torch.tensor([0.5])
+    result = dict(boxes_3d=boxes_3d, labels_3d=labels_3d, scores_3d=scores_3d)
+    results = [result]
+    temp_kitti_result_dir = tempfile.mkdtemp()
+    det_annos = self.bbox2result_kitti(
+        results, classes, submission_prefix=temp_kitti_result_dir)
+    expected_file_path = os.path.join(temp_kitti_result_dir, '000000.txt')
+    expected_name = np.array(['Pedestrian'])
+    expected_dimensions = np.array([1.2000, 1.8900, 0.4800])
+    expected_rotation_y = np.array([0.0100]) - np.pi
+    expected_score = np.array([0.5])
+    assert np.all(det_annos[0]['name'] == expected_name)
+    assert np.allclose(det_annos[0]['rotation_y'], expected_rotation_y)
+    assert np.allclose(det_annos[0]['score'], expected_score)
+    assert np.allclose(det_annos[0]['dimensions'], expected_dimensions)
+    assert os.path.exists(expected_file_path)
+    os.remove(expected_file_path)
+    os.removedirs(temp_kitti_result_dir)
+
+    temp_kitti_result_dir = tempfile.mkdtemp()
+    boxes_3d = LiDARInstance3DBoxes(torch.tensor([]))
+    labels_3d = torch.tensor([])
+    scores_3d = torch.tensor([])
+    empty_result = dict(
+        boxes_3d=boxes_3d, labels_3d=labels_3d, scores_3d=scores_3d)
+    results = [empty_result]
+    det_annos = self.bbox2result_kitti(
+        results, classes, submission_prefix=temp_kitti_result_dir)
+    expected_file_path = os.path.join(temp_kitti_result_dir, '000000.txt')
+    assert os.path.exists(expected_file_path)
+    os.remove(expected_file_path)
+    os.removedirs(temp_kitti_result_dir)
+
+
 def test_bbox2result_kitti2d():
-    data_root = 'tests/data/kitti'
-    ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
-    classes = ['Pedestrian', 'Cyclist', 'Car']
-    pts_prefix = 'velodyne_reduced'
-    pipeline = [{
-        'type': 'LoadPointsFromFile',
-        'coord_type': 'LIDAR',
-        'load_dim': 4,
-        'use_dim': 4,
-        'file_client_args': {
-            'backend': 'disk'
-        }
-    }, {
-        'type':
-        'MultiScaleFlipAug3D',
-        'img_scale': (1333, 800),
-        'pts_scale_ratio':
-        1,
-        'flip':
-        False,
-        'transforms': [{
-            'type': 'GlobalRotScaleTrans',
-            'rot_range': [-0.1, 0.1],
-            'scale_ratio_range': [0.9, 1.1],
-            'translation_std': [0, 0, 0]
-        }, {
-            'type': 'RandomFlip3D'
-        }, {
-            'type': 'PointsRangeFilter',
-            'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
-        }, {
-            'type': 'DefaultFormatBundle3D',
-            'class_names': ['Pedestrian', 'Cyclist', 'Car'],
-            'with_label': False
-        }, {
-            'type': 'Collect3D',
-            'keys': ['points']
-        }]
-    }]
-    modality = {'use_lidar': True, 'use_camera': False}
-    split = 'training'
-    self = KittiDataset(
-        data_root,
-        ann_file,
-        split,
-        pts_prefix,
-        pipeline,
-        classes,
-        modality,
-    )
+    data_root, ann_file, classes, pts_prefix,\
+        pipeline, modality, split = _generate_kitti_dataset_config()
+    self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
+                        classes, modality)
     bboxes = np.array([[[46.1218, -4.6496, -0.9275, 0.5316, 0.5],
                         [33.3189, 0.1981, 0.3136, 0.5656, 0.5]],
                        [[46.1366, -4.6404, -0.9510, 0.5162, 0.5],