update seg config (#1734)

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

@@ -58,6 +58,12 @@ test_pipeline = [
         use_color=True,
         load_dim=6,
         use_dim=[0, 1, 2, 3, 4, 5]),
+    dict(
+        type='LoadAnnotations3D',
+        with_bbox_3d=False,
+        with_label_3d=False,
+        with_mask_3d=False,
+        with_seg_3d=True),
     dict(type='NormalizePointsColor', color_mean=None),
     dict(
         # a wrapper in order to successfully call test function

configs/paconv/paconv_cuda_ssg_8x8_cosine_200e_s3dis_seg-3d-13class.py

@@ -4,9 +4,19 @@ _base_ = [
     '../_base_/schedules/seg_cosine_150e.py', '../_base_/default_runtime.py'
 ]
 
+# model settings
+model = dict(
+    decode_head=dict(
+        num_classes=13, ignore_index=13,
+        loss_decode=dict(class_weight=None)),  # S3DIS doesn't use class_weight
+    test_cfg=dict(
+        num_points=4096,
+        block_size=1.0,
+        sample_rate=0.5,
+        use_normalized_coord=True,
+        batch_size=12))
+
 # data settings
-class_names = ('ceiling', 'floor', 'wall', 'beam', 'column', 'window', 'door',
-               'table', 'chair', 'sofa', 'bookcase', 'board', 'clutter')
 num_points = 4096
 train_pipeline = [
     dict(
@@ -43,24 +53,11 @@ train_pipeline = [
         jitter_std=[0.01, 0.01, 0.01],
         clip_range=[-0.05, 0.05]),
     dict(type='RandomDropPointsColor', drop_ratio=0.2),
-    dict(type='DefaultFormatBundle3D', class_names=class_names),
-    dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
+    dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask'])
 ]
 
-data = dict(samples_per_gpu=8, train=dict(pipeline=train_pipeline))
-evaluation = dict(interval=1)
-
-# model settings
-model = dict(
-    decode_head=dict(
-        num_classes=13, ignore_index=13,
-        loss_decode=dict(class_weight=None)),  # S3DIS doesn't use class_weight
-    test_cfg=dict(
-        num_points=4096,
-        block_size=1.0,
-        sample_rate=0.5,
-        use_normalized_coord=True,
-        batch_size=12))
+train_dataloader = dict(batch_size=8, dataset=dict(pipeline=train_pipeline))
 
 # runtime settings
-runner = dict(max_epochs=200)
+val_cfg = dict(interval=1)
+train_cfg = dict(by_epoch=True, max_epochs=200)

configs/paconv/paconv_ssg_8x8_cosine_150e_s3dis_seg-3d-13class.py

@@ -4,18 +4,17 @@ _base_ = [
     '../_base_/default_runtime.py'
 ]
 
-# file_client_args = dict(backend='disk')
-# Uncomment the following if use ceph or other file clients.
-# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
-# for more details.
-file_client_args = dict(
-    backend='petrel',
-    path_mapping=dict({
-        './data/s3dis/':
-        's3://openmmlab/datasets/detection3d/s3dis_processed/',
-        'data/s3dis/':
-        's3://openmmlab/datasets/detection3d/s3dis_processed/'
-    }))
+# model settings
+model = dict(
+    decode_head=dict(
+        num_classes=13, ignore_index=13,
+        loss_decode=dict(class_weight=None)),  # S3DIS doesn't use class_weight
+    test_cfg=dict(
+        num_points=4096,
+        block_size=1.0,
+        sample_rate=0.5,
+        use_normalized_coord=True,
+        batch_size=12))
 
 # data settings
 num_points = 4096
@@ -57,17 +56,5 @@ train_pipeline = [
     dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask'])
 ]
 
-# model settings
-model = dict(
-    decode_head=dict(
-        num_classes=13, ignore_index=13,
-        loss_decode=dict(class_weight=None)),  # S3DIS doesn't use class_weight
-    test_cfg=dict(
-        num_points=4096,
-        block_size=1.0,
-        sample_rate=0.5,
-        use_normalized_coord=True,
-        batch_size=12))
-
 train_dataloader = dict(batch_size=8, dataset=dict(pipeline=train_pipeline))
 val_cfg = dict(interval=1)

configs/pointnet2/pointnet2_msg_16x2_cosine_250e_scannet_seg-3d-20class.py

@@ -4,10 +4,6 @@ _base_ = [
     '../_base_/schedules/seg_cosine_200e.py', '../_base_/default_runtime.py'
 ]
 
-# data settings
-data = dict(samples_per_gpu=16)
-evaluation = dict(interval=5)
-
 # model settings
 model = dict(
     decode_head=dict(
@@ -30,7 +26,12 @@ model = dict(
         use_normalized_coord=False,
         batch_size=24))
 
+# data settings
+train_dataloader = dict(batch_size=16)
+
 # runtime settings
-checkpoint_config = dict(interval=5)
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
+val_cfg = dict(interval=5)
+
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-runner = dict(type='EpochBasedRunner', max_epochs=250)
+train_cfg = dict(by_epoch=True, max_epochs=250)

configs/pointnet2/pointnet2_msg_16x2_cosine_80e_s3dis_seg-3d-13class.py

@@ -4,10 +4,6 @@ _base_ = [
     '../_base_/schedules/seg_cosine_50e.py', '../_base_/default_runtime.py'
 ]
 
-# data settings
-data = dict(samples_per_gpu=16)
-evaluation = dict(interval=2)
-
 # model settings
 model = dict(
     backbone=dict(in_channels=9),  # [xyz, rgb, normalized_xyz]
@@ -21,7 +17,12 @@ model = dict(
         use_normalized_coord=True,
         batch_size=24))
 
+# data settings
+train_dataloader = dict(batch_size=16)
+
 # runtime settings
-checkpoint_config = dict(interval=2)
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=2))
+val_cfg = dict(interval=2)
+
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-runner = dict(type='EpochBasedRunner', max_epochs=80)
+train_cfg = dict(by_epoch=True, max_epochs=80)

configs/pointnet2/pointnet2_msg_xyz-only_16x2_cosine_250e_scannet_seg-3d-20class.py

@@ -4,11 +4,32 @@ _base_ = [
     '../_base_/schedules/seg_cosine_200e.py', '../_base_/default_runtime.py'
 ]
 
+# model settings
+model = dict(
+    backbone=dict(in_channels=3),  # only [xyz]
+    decode_head=dict(
+        num_classes=20,
+        ignore_index=20,
+        # `class_weight` is generated in data pre-processing, saved in
+        # `data/scannet/seg_info/train_label_weight.npy`
+        # you can copy paste the values here, or input the file path as
+        # `class_weight=data/scannet/seg_info/train_label_weight.npy`
+        loss_decode=dict(class_weight=[
+            2.389689, 2.7215734, 4.5944676, 4.8543367, 4.096086, 4.907941,
+            4.690836, 4.512031, 4.623311, 4.9242644, 5.358117, 5.360071,
+            5.019636, 4.967126, 5.3502126, 5.4023647, 5.4027233, 5.4169416,
+            5.3954206, 4.6971426
+        ])),
+    test_cfg=dict(
+        num_points=8192,
+        block_size=1.5,
+        sample_rate=0.5,
+        use_normalized_coord=False,
+        batch_size=24))
+
 # dataset settings
 # in this setting, we only use xyz as network input
 # so we need to re-write all the data pipeline
-dataset_type = 'ScanNetSegDataset'
-data_root = './data/scannet/'
 class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
                'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
                'curtain', 'refrigerator', 'showercurtrain', 'toilet', 'sink',
@@ -37,8 +58,7 @@ train_pipeline = [
         use_normalized_coord=False,
         enlarge_size=0.2,
         min_unique_num=None),
-    dict(type='DefaultFormatBundle3D', class_names=class_names),
-    dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
+    dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask'])
 ]
 test_pipeline = [
     dict(
@@ -48,6 +68,12 @@ test_pipeline = [
         use_color=False,
         load_dim=6,
         use_dim=[0, 1, 2]),
+    dict(
+        type='LoadAnnotations3D',
+        with_bbox_3d=False,
+        with_label_3d=False,
+        with_mask_3d=False,
+        with_seg_3d=True),
     dict(
         # a wrapper in order to successfully call test function
         # actually we don't perform test-time-aug
@@ -66,68 +92,17 @@ test_pipeline = [
                 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'])
-        ])
+        ]),
+    dict(type='Pack3DDetInputs', keys=['points'])
 ]
-data = dict(
-    samples_per_gpu=16,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_train.pkl',
-        pipeline=train_pipeline,
-        classes=class_names,
-        test_mode=False,
-        ignore_index=len(class_names),
-        scene_idxs=data_root + 'seg_info/train_resampled_scene_idxs.npy'),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_val.pkl',
-        pipeline=test_pipeline,
-        classes=class_names,
-        test_mode=True,
-        ignore_index=len(class_names)),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_val.pkl',
-        pipeline=test_pipeline,
-        classes=class_names,
-        test_mode=True,
-        ignore_index=len(class_names)))
 
-evaluation = dict(interval=5)
-
-# model settings
-model = dict(
-    backbone=dict(in_channels=3),  # only [xyz]
-    decode_head=dict(
-        num_classes=20,
-        ignore_index=20,
-        # `class_weight` is generated in data pre-processing, saved in
-        # `data/scannet/seg_info/train_label_weight.npy`
-        # you can copy paste the values here, or input the file path as
-        # `class_weight=data/scannet/seg_info/train_label_weight.npy`
-        loss_decode=dict(class_weight=[
-            2.389689, 2.7215734, 4.5944676, 4.8543367, 4.096086, 4.907941,
-            4.690836, 4.512031, 4.623311, 4.9242644, 5.358117, 5.360071,
-            5.019636, 4.967126, 5.3502126, 5.4023647, 5.4027233, 5.4169416,
-            5.3954206, 4.6971426
-        ])),
-    test_cfg=dict(
-        num_points=8192,
-        block_size=1.5,
-        sample_rate=0.5,
-        use_normalized_coord=False,
-        batch_size=24))
+train_dataloader = dict(batch_size=16, dataset=dict(pipeline=train_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+val_dataloader = test_dataloader
 
 # runtime settings
-checkpoint_config = dict(interval=5)
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
+val_cfg = dict(interval=5)
+
 # PointNet2-MSG needs longer training time than PointNet2-SSG
-runner = dict(type='EpochBasedRunner', max_epochs=250)
+train_cfg = dict(by_epoch=True, max_epochs=250)

configs/pointnet2/pointnet2_ssg_16x2_cosine_200e_scannet_seg-3d-20class.py

@@ -30,5 +30,5 @@ model = dict(
 train_dataloader = dict(batch_size=16)
 
 # runtime settings
-default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5), )
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
 val_cfg = dict(interval=5)

configs/pointnet2/pointnet2_ssg_xyz-only_16x2_cosine_200e_scannet_seg-3d-20class.py

@@ -4,11 +4,32 @@ _base_ = [
     '../_base_/schedules/seg_cosine_200e.py', '../_base_/default_runtime.py'
 ]
 
+# model settings
+model = dict(
+    backbone=dict(in_channels=3),  # only [xyz]
+    decode_head=dict(
+        num_classes=20,
+        ignore_index=20,
+        # `class_weight` is generated in data pre-processing, saved in
+        # `data/scannet/seg_info/train_label_weight.npy`
+        # you can copy paste the values here, or input the file path as
+        # `class_weight=data/scannet/seg_info/train_label_weight.npy`
+        loss_decode=dict(class_weight=[
+            2.389689, 2.7215734, 4.5944676, 4.8543367, 4.096086, 4.907941,
+            4.690836, 4.512031, 4.623311, 4.9242644, 5.358117, 5.360071,
+            5.019636, 4.967126, 5.3502126, 5.4023647, 5.4027233, 5.4169416,
+            5.3954206, 4.6971426
+        ])),
+    test_cfg=dict(
+        num_points=8192,
+        block_size=1.5,
+        sample_rate=0.5,
+        use_normalized_coord=False,
+        batch_size=24))
+
 # dataset settings
 # in this setting, we only use xyz as network input
 # so we need to re-write all the data pipeline
-dataset_type = 'ScanNetSegDataset'
-data_root = './data/scannet/'
 class_names = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
                'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
                'curtain', 'refrigerator', 'showercurtrain', 'toilet', 'sink',
@@ -37,8 +58,7 @@ train_pipeline = [
         use_normalized_coord=False,
         enlarge_size=0.2,
         min_unique_num=None),
-    dict(type='DefaultFormatBundle3D', class_names=class_names),
-    dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
+    dict(type='Pack3DDetInputs', keys=['points', 'pts_semantic_mask'])
 ]
 test_pipeline = [
     dict(
@@ -48,6 +68,12 @@ test_pipeline = [
         use_color=False,
         load_dim=6,
         use_dim=[0, 1, 2]),
+    dict(
+        type='LoadAnnotations3D',
+        with_bbox_3d=False,
+        with_label_3d=False,
+        with_mask_3d=False,
+        with_seg_3d=True),
     dict(
         # a wrapper in order to successfully call test function
         # actually we don't perform test-time-aug
@@ -66,66 +92,14 @@ test_pipeline = [
                 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'])
-        ])
+        ]),
+    dict(type='Pack3DDetInputs', keys=['points'])
 ]
-data = dict(
-    samples_per_gpu=16,
-    workers_per_gpu=4,
-    train=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_train.pkl',
-        pipeline=train_pipeline,
-        classes=class_names,
-        test_mode=False,
-        ignore_index=len(class_names),
-        scene_idxs=data_root + 'seg_info/train_resampled_scene_idxs.npy'),
-    val=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_val.pkl',
-        pipeline=test_pipeline,
-        classes=class_names,
-        test_mode=True,
-        ignore_index=len(class_names)),
-    test=dict(
-        type=dataset_type,
-        data_root=data_root,
-        ann_file=data_root + 'scannet_infos_val.pkl',
-        pipeline=test_pipeline,
-        classes=class_names,
-        test_mode=True,
-        ignore_index=len(class_names)))
 
-evaluation = dict(interval=5)
-
-# model settings
-model = dict(
-    backbone=dict(in_channels=3),  # only [xyz]
-    decode_head=dict(
-        num_classes=20,
-        ignore_index=20,
-        # `class_weight` is generated in data pre-processing, saved in
-        # `data/scannet/seg_info/train_label_weight.npy`
-        # you can copy paste the values here, or input the file path as
-        # `class_weight=data/scannet/seg_info/train_label_weight.npy`
-        loss_decode=dict(class_weight=[
-            2.389689, 2.7215734, 4.5944676, 4.8543367, 4.096086, 4.907941,
-            4.690836, 4.512031, 4.623311, 4.9242644, 5.358117, 5.360071,
-            5.019636, 4.967126, 5.3502126, 5.4023647, 5.4027233, 5.4169416,
-            5.3954206, 4.6971426
-        ])),
-    test_cfg=dict(
-        num_points=8192,
-        block_size=1.5,
-        sample_rate=0.5,
-        use_normalized_coord=False,
-        batch_size=24))
+train_dataloader = dict(batch_size=16, dataset=dict(pipeline=train_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+val_dataloader = test_dataloader
 
 # runtime settings
-checkpoint_config = dict(interval=5)
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=5))
+val_cfg = dict(interval=5)