Merge branch 'indoor_pipeline' into 'master'

Indoor pipeline

See merge request open-mmlab/mmdet.3d!27

mmdet3d/datasets/pipelines/formating.py

@@ -40,7 +40,8 @@ class DefaultFormatBundle(object):
                 results['img'] = DC(to_tensor(img), stack=True)
         for key in [
                 'proposals', 'gt_bboxes', 'gt_bboxes_3d', 'gt_bboxes_ignore',
-                'gt_labels', 'gt_labels_3d'
+                'gt_labels', 'gt_labels_3d', 'pts_instance_mask',
+                'pts_semantic_mask'
         ]:
             if key not in results:
                 continue
@@ -127,6 +128,7 @@ class DefaultFormatBundle3D(DefaultFormatBundle):
                 gt_bboxes_3d_mask = results['gt_bboxes_3d_mask']
                 results['gt_bboxes_3d'] = results['gt_bboxes_3d'][
                     gt_bboxes_3d_mask]
+                if 'gt_names_3d' in results:
                     results['gt_names_3d'] = results['gt_names_3d'][
                         gt_bboxes_3d_mask]
             if 'gt_bboxes_mask' in results:
@@ -151,8 +153,10 @@ class DefaultFormatBundle3D(DefaultFormatBundle):
                                                     dtype=np.int64)
                 # we still assume one pipeline for one frame LiDAR
                 # thus, the 3D name is list[string]
+                if 'gt_names_3d' in results:
                     results['gt_labels_3d'] = np.array([
-                    self.class_names.index(n) for n in results['gt_names_3d']
+                        self.class_names.index(n)
+                        for n in results['gt_names_3d']
                     ],
                                                        dtype=np.int64)
         results = super(DefaultFormatBundle3D, self).__call__(results)

mmdet3d/datasets/pipelines/indoor_augment.py

@@ -133,7 +133,7 @@ class IndoorGlobalRotScale(object):
 
     def __init__(self, use_height=True, rot_range=None, scale_range=None):
         self.use_height = use_height
-        self.rot_range = rot_range
+        self.rot_range = np.pi * np.array(rot_range)
         self.scale_range = scale_range
 
     def _rotz(self, t):

mmdet3d/datasets/pipelines/indoor_loading.py

@@ -92,8 +92,8 @@ class IndoorLoadAnnotations3D(object):
 
         mmcv.check_file_exist(pts_instance_mask_path)
         mmcv.check_file_exist(pts_semantic_mask_path)
-        pts_instance_mask = np.load(pts_instance_mask_path)
-        pts_semantic_mask = np.load(pts_semantic_mask_path)
+        pts_instance_mask = np.load(pts_instance_mask_path).astype(np.int)
+        pts_semantic_mask = np.load(pts_semantic_mask_path).astype(np.int)
         results['pts_instance_mask'] = pts_instance_mask
         results['pts_semantic_mask'] = pts_semantic_mask
 

tests/test_indoor_augment.py → tests/test_pipeline/test_indoor_augment.py

@@ -64,7 +64,7 @@ def test_indoor_flip_data():
 def test_global_rot_scale():
     np.random.seed(0)
     sunrgbd_augment = IndoorGlobalRotScale(
-        True, rot_range=[-np.pi / 6, np.pi / 6], scale_range=[0.85, 1.15])
+        True, rot_range=[-1 / 6, 1 / 6], scale_range=[0.85, 1.15])
     sunrgbd_results = dict()
     sunrgbd_results['points'] = np.array(
         [[1.02828765e+00, 3.65790772e+00, 1.97294697e-01, 1.61959505e+00],
@@ -101,7 +101,7 @@ def test_global_rot_scale():
 
     np.random.seed(0)
     scannet_augment = IndoorGlobalRotScale(
-        True, rot_range=[-np.pi * 1 / 36, np.pi * 1 / 36], scale_range=None)
+        True, rot_range=[-1 * 1 / 36, 1 / 36], scale_range=None)
     scannet_results = dict()
     scannet_results['points'] = np.array(
         [[1.6110241e+00, -1.6903955e-01, 5.8115810e-01, 5.9897250e-01],

tests/test_indoor_loading.py → tests/test_pipeline/test_indoor_loading.py

@@ -39,15 +39,16 @@ def test_load_annotations3D():
     sunrgbd_info = mmcv.load('./tests/data/sunrgbd/sunrgbd_infos.pkl')[0]
     if sunrgbd_info['annos']['gt_num'] != 0:
         sunrgbd_gt_bboxes_3d = sunrgbd_info['annos']['gt_boxes_upright_depth']
-        sunrgbd_gt_labels = sunrgbd_info['annos']['class'].reshape(-1, 1)
-        sunrgbd_gt_bboxes_3d_mask = np.ones_like(sunrgbd_gt_labels)
+        sunrgbd_gt_labels_3d = sunrgbd_info['annos']['class']
+        sunrgbd_gt_bboxes_3d_mask = np.ones_like(
+            sunrgbd_gt_labels_3d, dtype=np.bool)
     else:
         sunrgbd_gt_bboxes_3d = np.zeros((1, 6), dtype=np.float32)
-        sunrgbd_gt_labels = np.zeros((1, 1))
-        sunrgbd_gt_bboxes_3d_mask = np.zeros((1, 1))
+        sunrgbd_gt_labels_3d = np.zeros((1, ))
+        sunrgbd_gt_bboxes_3d_mask = np.zeros((1, ), dtype=np.bool)
     assert sunrgbd_gt_bboxes_3d.shape == (3, 7)
-    assert sunrgbd_gt_labels.shape == (3, 1)
-    assert sunrgbd_gt_bboxes_3d_mask.shape == (3, 1)
+    assert sunrgbd_gt_labels_3d.shape == (3, )
+    assert sunrgbd_gt_bboxes_3d_mask.shape == (3, )
 
     scannet_info = mmcv.load('./tests/data/scannet/scannet_infos.pkl')[0]
     scannet_load_annotations3D = IndoorLoadAnnotations3D()
@@ -55,29 +56,29 @@ def test_load_annotations3D():
     data_path = './tests/data/scannet/scannet_train_instance_data'
     if scannet_info['annos']['gt_num'] != 0:
         scannet_gt_bboxes_3d = scannet_info['annos']['gt_boxes_upright_depth']
-        scannet_gt_labels = scannet_info['annos']['class'].reshape(-1, 1)
-        scannet_gt_bboxes_3d_mask = np.ones_like(scannet_gt_labels)
+        scannet_gt_labels_3d = scannet_info['annos']['class']
+        scannet_gt_bboxes_3d_mask = np.ones_like(
+            scannet_gt_labels_3d, dtype=np.bool)
     else:
         scannet_gt_bboxes_3d = np.zeros((1, 6), dtype=np.float32)
-        scannet_gt_labels = np.zeros((1, 1))
-        scannet_gt_bboxes_3d_mask = np.zeros((1, 1))
+        scannet_gt_labels_3d = np.zeros((1, ))
+        scannet_gt_bboxes_3d_mask = np.zeros((1, ), dtype=np.bool)
     scan_name = scannet_info['point_cloud']['lidar_idx']
     scannet_results['pts_instance_mask_path'] = osp.join(
         data_path, f'{scan_name}_ins_label.npy')
     scannet_results['pts_semantic_mask_path'] = osp.join(
         data_path, f'{scan_name}_sem_label.npy')
-    scannet_results['info'] = scannet_info
     scannet_results['gt_bboxes_3d'] = scannet_gt_bboxes_3d
-    scannet_results['gt_labels'] = scannet_gt_labels
+    scannet_results['gt_labels_3d'] = scannet_gt_labels_3d
     scannet_results['gt_bboxes_3d_mask'] = scannet_gt_bboxes_3d_mask
     scannet_results = scannet_load_annotations3D(scannet_results)
     scannet_gt_boxes = scannet_results['gt_bboxes_3d']
-    scannet_gt_lbaels = scannet_results['gt_labels']
+    scannet_gt_lbaels = scannet_results['gt_labels_3d']
     scannet_gt_boxes_mask = scannet_results['gt_bboxes_3d_mask']
     scannet_pts_instance_mask = scannet_results['pts_instance_mask']
     scannet_pts_semantic_mask = scannet_results['pts_semantic_mask']
     assert scannet_gt_boxes.shape == (27, 6)
-    assert scannet_gt_lbaels.shape == (27, 1)
-    assert scannet_gt_boxes_mask.shape == (27, 1)
+    assert scannet_gt_lbaels.shape == (27, )
+    assert scannet_gt_boxes_mask.shape == (27, )
     assert scannet_pts_instance_mask.shape == (100, )
     assert scannet_pts_semantic_mask.shape == (100, )

tests/test_pipeline/test_indoor_pipeline.py

+import os.path as osp
+
+import mmcv
+import numpy as np
+
+from mmdet3d.datasets.pipelines import Compose
+
+
+def test_scannet_pipeline():
+    class_names = ('cabinet', 'bed', 'chair', 'sofa', 'table', 'door',
+                   'window', 'bookshelf', 'picture', 'counter', 'desk',
+                   'curtain', 'refrigerator', 'showercurtrain', 'toilet',
+                   'sink', 'bathtub', 'garbagebin')
+
+    np.random.seed(0)
+    pipelines = [
+        dict(
+            type='IndoorLoadPointsFromFile',
+            use_height=True,
+            load_dim=6,
+            use_dim=[0, 1, 2]),
+        dict(type='IndoorLoadAnnotations3D'),
+        dict(type='IndoorPointSample', num_points=5),
+        dict(type='IndoorFlipData', flip_ratio_yz=1.0, flip_ratio_xz=1.0),
+        dict(
+            type='IndoorGlobalRotScale',
+            use_height=True,
+            rot_range=[-1 / 36, 1 / 36],
+            scale_range=None),
+        dict(type='DefaultFormatBundle3D', class_names=class_names),
+        dict(
+            type='Collect3D',
+            keys=[
+                'points', 'gt_bboxes_3d', 'gt_labels_3d', 'pts_semantic_mask',
+                'pts_instance_mask'
+            ]),
+    ]
+    pipeline = Compose(pipelines)
+    info = mmcv.load('./tests/data/scannet/scannet_infos.pkl')[0]
+    results = dict()
+    data_path = './tests/data/scannet/scannet_train_instance_data'
+    results['data_path'] = data_path
+    scan_name = info['point_cloud']['lidar_idx']
+    results['pts_filename'] = osp.join(data_path, f'{scan_name}_vert.npy')
+    if info['annos']['gt_num'] != 0:
+        scannet_gt_bboxes_3d = info['annos']['gt_boxes_upright_depth']
+        scannet_gt_labels_3d = info['annos']['class']
+        scannet_gt_bboxes_3d_mask = np.ones_like(
+            scannet_gt_labels_3d, dtype=np.bool)
+    else:
+        scannet_gt_bboxes_3d = np.zeros((1, 6), dtype=np.float32)
+        scannet_gt_labels_3d = np.zeros((1, ))
+        scannet_gt_bboxes_3d_mask = np.zeros((1, ), dtype=np.bool)
+    scan_name = info['point_cloud']['lidar_idx']
+
+    results['pts_instance_mask_path'] = osp.join(data_path,
+                                                 f'{scan_name}_ins_label.npy')
+    results['pts_semantic_mask_path'] = osp.join(data_path,
+                                                 f'{scan_name}_sem_label.npy')
+    results['gt_bboxes_3d'] = scannet_gt_bboxes_3d
+    results['gt_labels_3d'] = scannet_gt_labels_3d
+    results['gt_bboxes_3d_mask'] = scannet_gt_bboxes_3d_mask
+
+    results = pipeline(results)
+
+    points = results['points']._data
+    gt_bboxes_3d = results['gt_bboxes_3d']._data
+    gt_labels_3d = results['gt_labels_3d']._data
+    pts_semantic_mask = results['pts_semantic_mask']._data
+    pts_instance_mask = results['pts_instance_mask']._data
+    expected_points = np.array(
+        [[-2.9078157, -1.9569951, 2.3543026, 2.389488],
+         [-0.71360034, -3.4359822, 2.1330001, 2.1681855],
+         [-1.332374, 1.474838, -0.04405887, -0.00887359],
+         [2.1336637, -1.3265059, -0.02880373, 0.00638155],
+         [0.43895668, -3.0259454, 1.5560012, 1.5911865]])
+    expected_gt_bboxes_3d = np.array([
+        [-1.5005362, -3.512584, 1.8565295, 1.7457027, 0.24149807, 0.57235193],
+        [-2.8848705, 3.4961755, 1.5268247, 0.66170084, 0.17433672, 0.67153597],
+        [-1.1585636, -2.192365, 0.61649567, 0.5557011, 2.5375574, 1.2144762],
+        [-2.930457, -2.4856408, 0.9722377, 0.6270478, 1.8461524, 0.28697443],
+        [3.3114715, -0.00476722, 1.0712197, 0.46191898, 3.8605113, 2.1603441]
+    ])
+    expected_gt_labels_3d = np.array([
+        6, 6, 4, 9, 11, 11, 10, 0, 15, 17, 17, 17, 3, 12, 4, 4, 14, 1, 0, 0, 0,
+        0, 0, 0, 5, 5, 5
+    ])
+    expected_pts_semantic_mask = np.array([3, 1, 2, 2, 15])
+    expected_pts_instance_mask = np.array([44, 22, 10, 10, 57])
+    assert np.allclose(points, expected_points)
+    assert np.allclose(gt_bboxes_3d[:5, :], expected_gt_bboxes_3d)
+    assert np.all(gt_labels_3d.numpy() == expected_gt_labels_3d)
+    assert np.all(pts_semantic_mask.numpy() == expected_pts_semantic_mask)
+    assert np.all(pts_instance_mask.numpy() == expected_pts_instance_mask)
+
+
+def test_sunrgbd_pipeline():
+    class_names = ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
+                   'dresser', 'night_stand', 'bookshelf', 'bathtub')
+    np.random.seed(0)
+    pipelines = [
+        dict(
+            type='IndoorLoadPointsFromFile',
+            use_height=True,
+            load_dim=6,
+            use_dim=[0, 1, 2]),
+        dict(type='IndoorFlipData', flip_ratio_yz=1.0),
+        dict(
+            type='IndoorGlobalRotScale',
+            use_height=True,
+            rot_range=[-1 / 6, 1 / 6],
+            scale_range=[0.85, 1.15]),
+        dict(type='IndoorPointSample', num_points=5),
+        dict(type='DefaultFormatBundle3D', class_names=class_names),
+        dict(
+            type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d']),
+    ]
+    pipeline = Compose(pipelines)
+    results = dict()
+    info = mmcv.load('./tests/data/sunrgbd/sunrgbd_infos.pkl')[0]
+    data_path = './tests/data/sunrgbd/sunrgbd_trainval'
+    scan_name = info['point_cloud']['lidar_idx']
+    results['pts_filename'] = osp.join(data_path, 'lidar',
+                                       f'{scan_name:06d}.npy')
+
+    if info['annos']['gt_num'] != 0:
+        gt_bboxes_3d = info['annos']['gt_boxes_upright_depth']
+        gt_labels_3d = info['annos']['class']
+        gt_bboxes_3d_mask = np.ones_like(gt_labels_3d, dtype=np.bool)
+    else:
+        gt_bboxes_3d = np.zeros((1, 6), dtype=np.float32)
+        gt_labels_3d = np.zeros((1, ))
+        gt_bboxes_3d_mask = np.zeros((1, ), dtype=np.bool)
+
+    results['gt_bboxes_3d'] = gt_bboxes_3d
+    results['gt_labels_3d'] = gt_labels_3d
+    results['gt_bboxes_3d_mask'] = gt_bboxes_3d_mask
+    results = pipeline(results)
+    points = results['points']._data
+    gt_bboxes_3d = results['gt_bboxes_3d']._data
+    gt_labels_3d = results['gt_labels_3d']._data
+    expected_points = np.array(
+        [[0.6570105, 1.5538014, 0.24514851, 1.0165423],
+         [0.656101, 1.558591, 0.21755838, 0.98895216],
+         [0.6293659, 1.5679953, -0.10004003, 0.67135376],
+         [0.6068739, 1.5974995, -0.41063973, 0.36075398],
+         [0.6464709, 1.5573514, 0.15114647, 0.9225402]])
+    expected_gt_bboxes_3d = np.array([[
+        -2.012483, 3.9473376, -0.25446942, 2.3730404, 1.9457763, 2.0303352,
+        1.2205974
+    ],
+                                      [
+                                          -3.7036808, 4.2396426, -0.81091917,
+                                          0.6032123, 0.91040343, 1.003341,
+                                          1.2662518
+                                      ],
+                                      [
+                                          0.6528646, 2.1638472, -0.15228128,
+                                          0.7347852, 1.6113238, 2.1694272,
+                                          2.81404
+                                      ]])
+    expected_gt_labels_3d = np.array([0, 7, 6])
+    assert np.allclose(gt_bboxes_3d, expected_gt_bboxes_3d)
+    assert np.allclose(gt_labels_3d.flatten(), expected_gt_labels_3d)
+    assert np.allclose(points, expected_points)