change seed and names

mmdet3d/datasets/pipelines/indoor_sample.py

@@ -21,8 +21,7 @@ class PointSample(object):
                                points,
                                num_samples,
                                replace=None,
-                               return_choices=False,
-                               seed=None):
+                               return_choices=False):
         """Points Random Sampling.
 
         Sample points to a certain number.
@@ -37,8 +36,6 @@ class PointSample(object):
             points (ndarray): 3D Points.
             choices (ndarray): The generated random samples
         """
-        if seed is not None:
-            np.random.seed(seed)
         if replace is None:
             replace = (points.shape[0] < num_samples)
         choices = np.random.choice(
@@ -49,21 +46,21 @@ class PointSample(object):
             return points[choices]
 
     def __call__(self, results, seed=None):
-        point_cloud = results.get('point_cloud', None)
-        pcl_color = results.get('pcl_color', None)
-        point_cloud, choices = self.points_random_sampling(
-            point_cloud, self.num_points, return_choices=True, seed=seed)
-        results['point_cloud'] = point_cloud
+        points = results.get('points', None)
+        pts_color = results.get('pts_color', None)
+        points, choices = self.points_random_sampling(
+            points, self.num_points, return_choices=True)
+        results['points'] = points
 
-        if pcl_color is not None:
-            pcl_color = pcl_color[choices]
+        if pts_color is not None:
+            pts_color = pts_color[choices]
             instance_labels = results.get('instance_labels', None)
             semantic_labels = results.get('semantic_labels', None)
             instance_labels = instance_labels[choices]
             semantic_labels = semantic_labels[choices]
             results['instance_labels'] = instance_labels
             results['semantic_labels'] = semantic_labels
-            results['pcl_color'] = pcl_color
+            results['pts_color'] = pts_color
 
         return results
 

tests/test_indoor_sample.py

@@ -4,10 +4,10 @@ from mmdet3d.datasets.pipelines.indoor_sample import PointSample
 
 
 def test_indoor_sample():
+    np.random.seed(0)
     scannet_sample_points = PointSample(5)
     scannet_results = dict()
-    scannet_point_cloud = np.array(
-        [[1.0719866, -0.7870435, 0.8408122, 0.9196809],
+    scannet_points = np.array([[1.0719866, -0.7870435, 0.8408122, 0.9196809],
                                [1.103661, 0.81065744, 2.6616862, 2.7405548],
                                [1.0276475, 1.5061463, 2.6174362, 2.6963048],
                                [-0.9709588, 0.6750515, 0.93901765, 1.0178864],
@@ -17,35 +17,35 @@ def test_indoor_sample():
                                [1.1188195, -0.99211365, 2.5551798, 2.6340485],
                                [-0.9186557, -1.7041215, 2.0562649, 2.1351335],
                                [-1.0128691, -1.3394243, 0.040936, 0.1198047]])
-    scannet_results['point_cloud'] = scannet_point_cloud
+    scannet_results['points'] = scannet_points
     scannet_instance_labels = np.array([15, 12, 11, 38, 0, 18, 17, 12, 17, 0])
     scannet_results['instance_labels'] = scannet_instance_labels
-    scannet_pcl_color = np.array([[77., 74., 63.], [176., 166., 156.],
+    scannet_pts_color = np.array([[77., 74., 63.], [176., 166., 156.],
                                   [178., 164., 153.], [240., 235., 237.],
                                   [58., 58., 59.], [245., 236., 229.],
                                   [158., 148., 141.], [195., 184., 178.],
                                   [193., 181., 174.], [105., 102., 97.]])
-    scannet_results['pcl_color'] = scannet_pcl_color
+    scannet_results['pts_color'] = scannet_pts_color
     scannet_semantic_labels = np.array([38, 1, 1, 40, 0, 40, 1, 1, 1, 0])
     scannet_results['semantic_labels'] = scannet_semantic_labels
-
     scannet_results = scannet_sample_points(scannet_results, 0)
-    scannet_point_cloud_result = scannet_results.get('point_cloud', None)
-    scannet_pcl_color_result = scannet_results.get('pcl_color', None)
+    scannet_point_cloud_result = scannet_results.get('points', None)
+    scannet_pcl_color_result = scannet_results.get('pts_color', None)
     scannet_instance_labels_result = scannet_results.get(
         'instance_labels', None)
     scannet_semantic_labels_result = scannet_results.get(
         'semantic_labels', None)
     scannet_choices = np.array([2, 8, 4, 9, 1])
-    assert np.allclose(scannet_point_cloud[scannet_choices],
+    assert np.allclose(scannet_points[scannet_choices],
                        scannet_point_cloud_result)
-    assert np.allclose(scannet_pcl_color[scannet_choices],
+    assert np.allclose(scannet_pts_color[scannet_choices],
                        scannet_pcl_color_result)
     assert np.all(scannet_instance_labels[scannet_choices] ==
                   scannet_instance_labels_result)
     assert np.all(scannet_semantic_labels[scannet_choices] ==
                   scannet_semantic_labels_result)
 
+    np.random.seed(0)
     sunrgbd_sample_points = PointSample(5)
     sunrgbd_results = dict()
     sunrgbd_point_cloud = np.array(
@@ -59,10 +59,9 @@ def test_indoor_sample():
          [-0.74624217, 1.5244724, -0.8678476, 0.41810507],
          [0.56485355, 1.5747732, -0.804522, 0.4814307],
          [-0.0913099, 1.3673826, -1.2800645, 0.00588822]])
-    sunrgbd_results['point_cloud'] = sunrgbd_point_cloud
-
+    sunrgbd_results['points'] = sunrgbd_point_cloud
     sunrgbd_results = sunrgbd_sample_points(sunrgbd_results, 0)
     sunrgbd_choices = np.array([2, 8, 4, 9, 1])
-    sunrgbd_point_cloud_result = sunrgbd_results.get('point_cloud', None)
+    sunrgbd_points_result = sunrgbd_results.get('points', None)
     assert np.allclose(sunrgbd_point_cloud[sunrgbd_choices],
-                       sunrgbd_point_cloud_result)
+                       sunrgbd_points_result)