-
Notifications
You must be signed in to change notification settings - Fork 7
/
td3d_is_scannet200-3d-198class.py
181 lines (176 loc) · 8.21 KB
/
td3d_is_scannet200-3d-198class.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
voxel_size = .02
padding = .08
n_points = 100000
class_names = ('chair', 'table', 'door', 'couch', 'cabinet', 'shelf', 'desk', 'office chair', 'bed', 'pillow', 'sink', 'picture', 'window', 'toilet', 'bookshelf', 'monitor', 'curtain', 'book', 'armchair', 'coffee table', 'box',
'refrigerator', 'lamp', 'kitchen cabinet', 'towel', 'clothes', 'tv', 'nightstand', 'counter', 'dresser', 'stool', 'cushion', 'plant', 'ceiling', 'bathtub', 'end table', 'dining table', 'keyboard', 'bag', 'backpack', 'toilet paper',
'printer', 'tv stand', 'whiteboard', 'blanket', 'shower curtain', 'trash can', 'closet', 'stairs', 'microwave', 'stove', 'shoe', 'computer tower', 'bottle', 'bin', 'ottoman', 'bench', 'board', 'washing machine', 'mirror', 'copier',
'basket', 'sofa chair', 'file cabinet', 'fan', 'laptop', 'shower', 'paper', 'person', 'paper towel dispenser', 'oven', 'blinds', 'rack', 'plate', 'blackboard', 'piano', 'suitcase', 'rail', 'radiator', 'recycling bin', 'container',
'wardrobe', 'soap dispenser', 'telephone', 'bucket', 'clock', 'stand', 'light', 'laundry basket', 'pipe', 'clothes dryer', 'guitar', 'toilet paper holder', 'seat', 'speaker', 'column', 'bicycle', 'ladder', 'bathroom stall', 'shower wall',
'cup', 'jacket', 'storage bin', 'coffee maker', 'dishwasher', 'paper towel roll', 'machine', 'mat', 'windowsill', 'bar', 'toaster', 'bulletin board', 'ironing board', 'fireplace', 'soap dish', 'kitchen counter', 'doorframe',
'toilet paper dispenser', 'mini fridge', 'fire extinguisher', 'ball', 'hat', 'shower curtain rod', 'water cooler', 'paper cutter', 'tray', 'shower door', 'pillar', 'ledge', 'toaster oven', 'mouse', 'toilet seat cover dispenser',
'furniture', 'cart', 'storage container', 'scale', 'tissue box', 'light switch', 'crate', 'power outlet', 'decoration', 'sign', 'projector', 'closet door', 'vacuum cleaner', 'candle', 'plunger', 'stuffed animal', 'headphones', 'dish rack',
'broom', 'guitar case', 'range hood', 'dustpan', 'hair dryer', 'water bottle', 'handicap bar', 'purse', 'vent', 'shower floor', 'water pitcher', 'mailbox', 'bowl', 'paper bag', 'alarm clock', 'music stand', 'projector screen', 'divider',
'laundry detergent', 'bathroom counter', 'object', 'bathroom vanity', 'closet wall', 'laundry hamper', 'bathroom stall door', 'ceiling light', 'trash bin', 'dumbbell', 'stair rail', 'tube', 'bathroom cabinet', 'cd case', 'closet rod',
'coffee kettle', 'structure', 'shower head', 'keyboard piano', 'case of water bottles', 'coat rack', 'storage organizer', 'folded chair', 'fire alarm', 'power strip', 'calendar', 'poster', 'potted plant', 'luggage', 'mattress')
model = dict(
type='TD3DInstanceSegmentor',
voxel_size=voxel_size,
backbone=dict(type='MinkResNet', in_channels=3, depth=34, norm='batch', return_stem=True, stride=1),
neck=dict(
type='NgfcTinySegmentationNeck',
in_channels=(64, 128, 256, 512),
out_channels=128),
head=dict(
type='TD3DInstanceHead',
in_channels=128,
n_reg_outs=6,
n_classes=len(class_names),
n_levels=4,
padding=padding,
voxel_size=voxel_size,
unet=dict(
type='MinkUNet14B',
in_channels=32,
out_channels=len(class_names) + 1,
D=3),
first_assigner=dict(
type='NgfcV2Assigner',
min_pts_threshold=18,
top_pts_threshold=8,
padding=padding),
second_assigner=dict(
type='MaxIoU3DAssigner',
threshold=.25),
roi_extractor=dict(
type='Mink3DRoIExtractor',
voxel_size=voxel_size,
padding=padding,
min_pts_threshold=10)),
train_cfg=dict(num_rois=2),
test_cfg=dict(
nms_pre=600,
iou_thr=.4,
score_thr=.1,
binary_score_thr=0.2))
optimizer = dict(type='AdamW', lr=0.001, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2))
lr_config = dict(policy='step', warmup=None, step=[28, 32])
runner = dict(type='EpochBasedRunner', max_epochs=33)
custom_hooks = [dict(type='EmptyCacheHook', after_iter=True)]
checkpoint_config = dict(interval=1, max_keep_ckpts=40)
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = None
load_from = None
resume_from = None
workflow = [('train', 1)]
dataset_type = 'ScanNet200InstanceSegDataset'
data_root = './data/scannet200/'
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
use_color=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='LoadAnnotations3D',
with_mask_3d=True,
with_seg_3d=True),
dict(
type='GlobalAlignment', rotation_axis=2),
dict(
type='PointSample', num_points=n_points),
dict(
type='PointSegClassMappingV2',
valid_cat_ids=(2, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 26, 27, 28, 29, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 44, 45, 46, 47, 48, 49, 50, 51, 52, 54, 55, 56, 57, 58, 59, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71,
72, 73, 74, 75, 76, 77, 78, 79, 80, 82, 84, 86, 87, 88, 89, 90, 93, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 110, 112, 115, 116, 118, 120, 121, 122, 125, 128, 130, 131, 132, 134, 136, 138, 139, 140, 141, 145, 148, 154,
155, 156, 157, 159, 161, 163, 165, 166, 168, 169, 170, 177, 180, 185, 188, 191, 193, 195, 202, 208, 213, 214, 221, 229, 230, 232, 233, 242, 250, 261, 264, 276, 283, 286, 300, 304, 312, 323, 325, 331, 342, 356, 370, 392, 395, 399, 408, 417,
488, 540, 562, 570, 572, 581, 609, 748, 776, 1156, 1163, 1164, 1165, 1166, 1167, 1168, 1169, 1170, 1171, 1172, 1173, 1174, 1175, 1176, 1178, 1179, 1180, 1181, 1182, 1183, 1184, 1185, 1186, 1187, 1188, 1189, 1190, 1191),
max_cat_id=1357),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=0.5,
flip_ratio_bev_vertical=0.5),
dict(
type='Elastic'),
dict(
type='MiniMosaic',
remaining_points_thr=0.3,
n_src_points=n_points),
dict(
type='GlobalRotScaleTransV2',
rot_range_z=[-3.14, 3.14],
rot_range_x_y=[-0.1308, 0.1308],
scale_ratio_range=[.8, 1.2],
translation_std=[.1, .1, .1],
shift_height=False),
dict(
type='BboxRecalculation'),
dict(type='NormalizePointsColor', color_mean=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'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
use_color=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(type='NormalizePointsColor', color_mean=None),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=8,
train=dict(
type='RepeatDataset',
times=10,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'scannet200_infos_train.pkl',
pipeline=train_pipeline,
filter_empty_gt=True,
classes=class_names,
box_type_3d='Depth')),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'scannet200_infos_val.pkl',
pipeline=test_pipeline,
filter_empty_gt=False,
classes=class_names,
test_mode=True,
box_type_3d='Depth'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'scannet200_infos_val.pkl',
pipeline=test_pipeline,
filter_empty_gt=False,
classes=class_names,
test_mode=True,
box_type_3d='Depth'))