add loading, change names, mmcv, empty line

mmdet3d/datasets/pipelines/loading.py

+import os.path as osp
+
+import mmcv
+import numpy as np
+
+from mmdet.datasets.registry import PIPELINES
+
+
+@PIPELINES.register_module
+class LoadPointsFromFile(object):
+
+    def __init__(self, points_dim=4, with_reflectivity=True):
+        self.points_dim = points_dim
+        self.with_reflectivity = with_reflectivity
+
+    def __call__(self, results):
+        if results['pts_prefix'] is not None:
+            filename = osp.join(results['pts_prefix'],
+                                results['img_info']['filename'])
+        else:
+            filename = results['img_info']['filename']
+        points = np.fromfile(
+            filename, dtype=np.float32).reshape(-1, self.points_dim)
+        results['points'] = points
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += '(points_dim={})'.format(self.points_dim)
+        repr_str += '(points_dim={})'.format(self.with_reflectivity)
+        return repr_str
+
+
+@PIPELINES.register_module
+class LoadMultiViewImageFromFiles(object):
+    """ Load multi channel images from a list of separate channel files.
+    Expects results['filename'] to be a list of filenames
+    """
+
+    def __init__(self, to_float32=False, color_type='unchanged'):
+        self.to_float32 = to_float32
+        self.color_type = color_type
+
+    def __call__(self, results):
+        if results['img_prefix'] is not None:
+            filename = [
+                osp.join(results['img_prefix'], fname)
+                for fname in results['img_info']['filename']
+            ]
+        else:
+            filename = results['img_info']['filename']
+        img = np.stack(
+            [mmcv.imread(name, self.color_type) for name in filename], axis=-1)
+        if self.to_float32:
+            img = img.astype(np.float32)
+        results['filename'] = filename
+        results['img'] = img
+        results['img_shape'] = img.shape
+        results['ori_shape'] = img.shape
+        # Set initial values for default meta_keys
+        results['pad_shape'] = img.shape
+        results['scale_factor'] = 1.0
+        num_channels = 1 if len(img.shape) < 3 else img.shape[2]
+        results['img_norm_cfg'] = dict(
+            mean=np.zeros(num_channels, dtype=np.float32),
+            std=np.ones(num_channels, dtype=np.float32),
+            to_rgb=False)
+        return results
+
+    def __repr__(self):
+        return "{} (to_float32={}, color_type='{}')".format(
+            self.__class__.__name__, self.to_float32, self.color_type)

tools/data_converter/indoor_converter.py

@@ -21,10 +21,10 @@ def create_indoor_info_file(data_path,
     """
     assert os.path.exists(data_path)
     assert pkl_prefix in ['sunrgbd', 'scannet']
-    if save_path is None:
-        save_path = data_path
+    save_path = data_path if save_path is None else save_path
     assert os.path.exists(save_path)
     train_filename = os.path.join(save_path, f'{pkl_prefix}_infos_train.pkl')
+
     val_filename = os.path.join(save_path, f'{pkl_prefix}_infos_val.pkl')
     if pkl_prefix == 'sunrgbd':
         train_dataset = SUNRGBDData(
@@ -35,10 +35,21 @@ def create_indoor_info_file(data_path,
         train_dataset = ScanNetData(root_path=data_path, split='train')
         val_dataset = ScanNetData(root_path=data_path, split='val')
     infos_train = train_dataset.get_infos(has_label=True)
-    with open(train_filename, 'wb') as f:
-        mmcv.dump(infos_train, f, 'pkl')
+
+    mmcv.dump(infos_train, train_filename, 'pkl')
     print(f'{pkl_prefix} info train file is saved to {train_filename}')
     infos_val = val_dataset.get_infos(has_label=True)
-    with open(val_filename, 'wb') as f:
-        mmcv.dump(infos_val, f, 'pkl')
+
+    mmcv.dump(infos_val, val_filename, 'pkl')
     print(f'{pkl_prefix} info val file is saved to {val_filename}')
+
+
+if __name__ == '__main__':
+    create_indoor_info_file(
+        data_path='./data/scannet',
+        pkl_prefix='scannet',
+        save_path='./data/scannet')
+    create_indoor_info_file(
+        data_path='./data/sunrgbd/sunrgbd_trainval',
+        pkl_prefix='sunrgbd',
+        save_path='./data/sunrgbd')

tools/data_converter/sunrgbd_data_utils.py

@@ -6,28 +6,28 @@ import numpy as np
 import scipy.io as sio
 
 
-def random_sampling(pc, num_points, replace=None, return_choices=False):
+def random_sampling(points, num_points, replace=None, return_choices=False):
     """Random Sampling.
 
     Sampling point cloud to a certain number of points.
 
     Args:
-        pc (ndarray): Point cloud.
+        points (ndarray): Point cloud.
         num_points (int): The number of samples.
         replace (bool): Whether the sample is with or without replacement.
         return_choices (bool): Whether to return choices.
 
     Returns:
-        pc (ndarray): Point cloud after sampling.
+        points (ndarray): Point cloud after sampling.
     """
 
     if replace is None:
-        replace = (pc.shape[0] < num_points)
-    choices = np.random.choice(pc.shape[0], num_points, replace=replace)
+        replace = (points.shape[0] < num_points)
+    choices = np.random.choice(points.shape[0], num_points, replace=replace)
     if return_choices:
-        return pc[choices], choices
+        return points[choices], choices
     else:
-        return pc[choices]
+        return points[choices]
 
 
 class SUNRGBDInstance(object):