[Fix] Fix small errors in seg dataset and cfgs (#487)

* fix small errors in seg dataset cfgs

* add box field to 3d seg dataset

* fix small bug in S3DIS data generation scripts

* fix small bugs in scannet data generation

configs/_base_/datasets/s3dis_seg-3d-13class.py

@@ -44,8 +44,30 @@ test_pipeline = [
         load_dim=6,
         use_dim=[0, 1, 2, 3, 4, 5]),
     dict(type='NormalizePointsColor', color_mean=None),
-    dict(type='DefaultFormatBundle3D', class_names=class_names),
-    dict(type='Collect3D', keys=['points'])
+    dict(
+        # a wrapper in order to successfully call test function
+        # actually we don't perform test-time-aug
+        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',
+                sync_2d=False,
+                flip_ratio_bev_horizontal=0.0,
+                flip_ratio_bev_vertical=0.0),
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['points'])
+        ])
 ]
 # construct a pipeline for data and gt loading in show function
 # please keep its loading function consistent with test_pipeline (e.g. client)
@@ -94,22 +116,24 @@ data = dict(
             data_root + f'seg_info/Area_{i}_resampled_scene_idxs.npy'
             for i in train_area
         ],
-        label_weight=[
+        label_weights=[
             data_root + f'seg_info/Area_{i}_label_weight.npy'
             for i in train_area
         ]),
     val=dict(
         type=dataset_type,
         data_root=data_root,
-        ann_file=data_root + f's3dis_infos_Area_{test_area}.pkl',
+        ann_files=data_root + f's3dis_infos_Area_{test_area}.pkl',
         pipeline=test_pipeline,
         classes=class_names,
         test_mode=True,
-        ignore_index=len(class_names)),
+        ignore_index=len(class_names),
+        scene_idxs=data_root +
+        f'seg_info/Area_{test_area}_resampled_scene_idxs.npy'),
     test=dict(
         type=dataset_type,
         data_root=data_root,
-        ann_file=data_root + f's3dis_infos_Area_{test_area}.pkl',
+        ann_files=data_root + f's3dis_infos_Area_{test_area}.pkl',
         pipeline=test_pipeline,
         classes=class_names,
         test_mode=True,

configs/_base_/datasets/scannet_seg-3d-20class.py

@@ -45,8 +45,30 @@ test_pipeline = [
         load_dim=6,
         use_dim=[0, 1, 2, 3, 4, 5]),
     dict(type='NormalizePointsColor', color_mean=None),
-    dict(type='DefaultFormatBundle3D', class_names=class_names),
-    dict(type='Collect3D', keys=['points'])
+    dict(
+        # a wrapper in order to successfully call test function
+        # actually we don't perform test-time-aug
+        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',
+                sync_2d=False,
+                flip_ratio_bev_horizontal=0.0,
+                flip_ratio_bev_vertical=0.0),
+            dict(
+                type='DefaultFormatBundle3D',
+                class_names=class_names,
+                with_label=False),
+            dict(type='Collect3D', keys=['points'])
+        ])
 ]
 # construct a pipeline for data and gt loading in show function
 # please keep its loading function consistent with test_pipeline (e.g. client)

data/s3dis/collect_indoor3d_data.py

 import argparse
 import mmcv
+from indoor3d_util import export
 from os import path as osp
 
-from .indoor3d_util import export
-
 parser = argparse.ArgumentParser()
 parser.add_argument(
     '--output-folder',

data/scannet/batch_load_scannet_data.py

@@ -52,6 +52,7 @@ def export_one_scan(scan_name,
         print(f'Num of care instances: {instance_bboxes.shape[0]}')
 
     if max_num_point is not None:
+        max_num_point = int(max_num_point)
         N = mesh_vertices.shape[0]
         if N > max_num_point:
             choices = np.random.choice(N, max_num_point, replace=False)

data/scannet/load_scannet_data.py

@@ -58,7 +58,7 @@ def export(mesh_file,
            meta_file,
            label_map_file,
            output_file=None,
-           is_train=True):
+           test_mode=False):
     """Export original files to vert, ins_label, sem_label and bbox file.
 
     Args:
@@ -69,8 +69,8 @@ def export(mesh_file,
         label_map_file (str): Path of the label_map_file.
         output_file (str): Path of the output folder.
             Default: None.
-        is_train (bool): Whether is generating training data with labels.
-            Default: True.
+        test_mode (bool): Whether is generating training data without labels.
+            Default: False.
 
     It returns a tuple, which containts the the following things:
         np.ndarray: Vertices of points data.
@@ -103,7 +103,7 @@ def export(mesh_file,
     mesh_vertices[:, 0:3] = pts[:, 0:3]
 
     # Load semantic and instance labels
-    if is_train:
+    if not test_mode:
         object_id_to_segs, label_to_segs = read_aggregation(agg_file)
         seg_to_verts, num_verts = read_segmentation(seg_file)
         label_ids = np.zeros(shape=(num_verts), dtype=np.uint32)
@@ -147,7 +147,7 @@ def export(mesh_file,
 
     if output_file is not None:
         np.save(output_file + '_vert.npy', mesh_vertices)
-        if is_train:
+        if not test_mode:
             np.save(output_file + '_sem_label.npy', label_ids)
             np.save(output_file + '_ins_label.npy', instance_ids)
             np.save(output_file + '_bbox.npy', instance_bboxes)

mmdet3d/datasets/custom_3d_seg.py

@@ -143,6 +143,7 @@ class Custom3DSegDataset(Dataset):
         results['pts_seg_fields'] = []
         results['mask_fields'] = []
         results['seg_fields'] = []
+        results['gt_bboxes_3d'] = []
 
     def prepare_train_data(self, index):
         """Training data preparation.

setup.cfg

@@ -8,6 +8,6 @@ line_length = 79
 multi_line_output = 0
 known_standard_library = setuptools
 known_first_party = mmdet,mmdet3d
-known_third_party = cv2,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,tensorflow,terminaltables,torch,trimesh,waymo_open_dataset
+known_third_party = cv2,indoor3d_util,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,tensorflow,terminaltables,torch,trimesh,waymo_open_dataset
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY