forked from hailanyi/VirConv
-
Notifications
You must be signed in to change notification settings - Fork 0
/
VirConv-T.yaml
349 lines (300 loc) · 9.97 KB
/
VirConv-T.yaml
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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
CLASS_NAMES: ['Car']
DATA_CONFIG:
_BASE_CONFIG_: cfgs/dataset_configs/kitti_dataset.yaml
DATASET: 'KittiDatasetMM'
INPUT_DISCARD_RATE: 0.8 # actually discard more than 90% virtual points of RGB image,
# as we only saved less than 50% RGB points during depth2points conversion.
MM_PATH: 'velodyne_depth'
ROT_NUM: 3
USE_VAN: True
DATA_SPLIT: {
'train': train,
'test': val
}
INFO_PATH: {
'train': [kitti_infos_train.pkl],
'test': [kitti_infos_val.pkl],
}
DATA_AUGMENTOR:
DISABLE_AUG_LIST: ['placeholder']
AUG_CONFIG_LIST:
- NAME: gt_sampling
USE_ROAD_PLANE: True
DB_INFO_PATH:
- kitti_dbinfos_train_mm.pkl
PREPARE: {
filter_by_min_points: ['Car:5', 'Pedestrian:5', 'Cyclist:5'],
filter_by_difficulty: [-1],
}
SAMPLE_GROUPS: ['Car:10', 'Pedestrian:10', 'Cyclist:10']
NUM_POINT_FEATURES: 8
DATABASE_WITH_FAKELIDAR: False
REMOVE_EXTRA_WIDTH: [0.0, 0.0, -0.2]
LIMIT_WHOLE_SCENE: False
- NAME: da_sampling
USE_ROAD_PLANE: True
DB_INFO_PATH:
- kitti_dbinfos_train_mm.pkl
PREPARE: {
filter_by_min_points: ['Car:5'],
filter_by_difficulty: [-1],
}
SAMPLE_GROUPS: ['Car:10']
MIN_SAMPLING_DIS: 0
MAX_SAMPLING_DIS: 20
OCCLUSION_NOISE: 0.2
OCCLUSION_OFFSET: 2.
SAMPLING_METHOD: 'LiDAR-aware'
VERT_RES: 0.006
HOR_RES: 0.003
NUM_POINT_FEATURES: 8
DATABASE_WITH_FAKELIDAR: False
REMOVE_EXTRA_WIDTH: [0.0, 0.0, -0.2]
LIMIT_WHOLE_SCENE: False
- NAME: random_local_noise
LOCAL_ROT_RANGE: [-0.78539816, 0.78539816]
TRANSLATION_STD: [1.0, 1.0, 0.5]
GLOBAL_ROT_RANGE: [0.0, 0.0]
EXTRA_WIDTH: [0.2, 0.2, 0.]
- NAME: random_world_rotation
WORLD_ROT_ANGLE: [-0.78539816, 0.78539816]
- NAME: random_world_flip
ALONG_AXIS_LIST: ['x']
- NAME: random_world_scaling
WORLD_SCALE_RANGE: [0.95, 1.05]
- NAME: random_local_trans
TRANSLATION_STD: [1.0, 1.0, 0.2]
- NAME: random_local_pyramid_aug
DROP_PROB: 0.25
SPARSIFY_PROB: 0.05
SPARSIFY_MAX_NUM: 50
SWAP_PROB: 0.1
SWAP_MAX_NUM: 50
X_TRANS:
AUG_CONFIG_LIST:
- NAME: world_rotation
WORLD_ROT_ANGLE: [0.3, 0.3, 0]
- NAME: world_flip
ALONG_AXIS_LIST: [0, 1., 1.]
- NAME: world_scaling
WORLD_SCALE_RANGE: [ 0.98, 1.02, 1.]
POINT_FEATURE_ENCODING: {
encoding_type: absolute_coordinates_encoding_mm,
used_feature_list: ['x', 'y', 'z', 'intensity'],
src_feature_list: ['x', 'y', 'z', 'intensity'],
num_features: 8
}
DATA_PROCESSOR:
- NAME: mask_points_and_boxes_outside_range
REMOVE_OUTSIDE_BOXES: True
- NAME: shuffle_points
SHUFFLE_ENABLED: {
'train': True,
'test': False
}
- NAME: transform_points_to_voxels
VOXEL_SIZE: [0.05, 0.05, 0.05]
MAX_POINTS_PER_VOXEL: 5
MAX_NUMBER_OF_VOXELS: {
'train': 16000, # each modality only uses 16000 voxels during training
'test': 40000
}
MODEL:
NAME: VoxelRCNN
VFE:
NAME: MeanVFE
MODEL: 'max'
BACKBONE_3D:
NAME: VirConv8x
NUM_FILTERS: [16, 32, 64, 64]
RETURN_NUM_FEATURES_AS_DICT: True
OUT_FEATURES: 64
MM: True
LAYER_DISCARD_RATE: 0.15
MAP_TO_BEV:
NAME: HeightCompression
NUM_BEV_FEATURES: 256
BACKBONE_2D:
NAME: BaseBEVBackbone
LAYER_NUMS: [4, 4]
LAYER_STRIDES: [1, 2]
NUM_FILTERS: [64, 128]
UPSAMPLE_STRIDES: [1, 2]
NUM_UPSAMPLE_FILTERS: [128, 128]
DENSE_HEAD:
NAME: AnchorHeadSingle
CLASS_AGNOSTIC: False
USE_DIRECTION_CLASSIFIER: True
DIR_OFFSET: 0.78539
DIR_LIMIT_OFFSET: 0.0
NUM_DIR_BINS: 2
ANCHOR_GENERATOR_CONFIG: [
{
'class_name': 'Car',
'anchor_sizes': [[3.9, 1.6, 1.56]],
'anchor_rotations': [0, 1.57],
'anchor_bottom_heights': [-1.78],
'align_center': False,
'feature_map_stride': 8,
'matched_threshold': 0.6,
'unmatched_threshold': 0.45
}
]
TARGET_ASSIGNER_CONFIG:
NAME: AxisAlignedTargetAssigner
POS_FRACTION: -1.0
SAMPLE_SIZE: 512
NORM_BY_NUM_EXAMPLES: False
MATCH_HEIGHT: False
BOX_CODER: ResidualCoder
LOSS_CONFIG:
LOSS_WEIGHTS: {
'cls_weight': 1.0,
'loc_weight': 2.0,
'dir_weight': 0.2,
'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
}
ROI_HEAD:
NAME: TEDMHead
CLASS_AGNOSTIC: True
ROT_NUM: 3
PART:
IN_CHANNEL: 256
SIZE: 7
GRID_OFFSETS: [0., 40.]
FEATMAP_STRIDE: 0.4
SHARED_FC: [256, 256]
CLS_FC: [256, 256]
REG_FC: [256, 256]
DP_RATIO: 0.01
NMS_CONFIG:
TRAIN:
NMS_TYPE: nms_gpu
MULTI_CLASSES_NMS: False
NMS_PRE_MAXSIZE: 4000
NMS_POST_MAXSIZE: 512
NMS_THRESH: 0.8
TEST:
NMS_TYPE: nms_gpu
MULTI_CLASSES_NMS: False
USE_FAST_NMS: True
SCORE_THRESH: 0.0
NMS_PRE_MAXSIZE: 2000
NMS_POST_MAXSIZE: 50
NMS_THRESH: 0.75
ROI_GRID_POOL:
FEATURES_SOURCE: ['x_conv3','x_conv4']
PRE_MLP: True
GRID_SIZE: 6
POOL_LAYERS:
x_conv3:
MLPS: [[32, 32], [32, 32]]
QUERY_RANGES: [[2, 2, 2], [4, 4, 4]]
POOL_RADIUS: [0.4, 0.8]
NSAMPLE: [16, 16]
POOL_METHOD: max_pool
x_conv4:
MLPS: [[32, 32], [32, 32]]
QUERY_RANGES: [[2, 2, 2], [4, 4, 4]]
POOL_RADIUS: [0.8, 1.6]
NSAMPLE: [16, 16]
POOL_METHOD: max_pool
ROI_GRID_POOL_MM:
FEATURES_SOURCE: ['x_conv3','x_conv4']
PRE_MLP: True
GRID_SIZE: 4
POOL_LAYERS:
x_conv3:
MLPS: [[32, 32], [32, 32]]
QUERY_RANGES: [[2, 2, 2], [4, 4, 4]]
POOL_RADIUS: [0.4, 0.8]
NSAMPLE: [16, 16]
POOL_METHOD: max_pool
x_conv4:
MLPS: [[32, 32], [32, 32]]
QUERY_RANGES: [[2, 2, 2], [4, 4, 4]]
POOL_RADIUS: [0.8, 1.6]
NSAMPLE: [16, 16]
POOL_METHOD: max_pool
TARGET_CONFIG:
BOX_CODER: ResidualCoder
STAGE0:
ROI_PER_IMAGE: 160
FG_RATIO: 0.5
SAMPLE_ROI_BY_EACH_CLASS: True
CLS_SCORE_TYPE: roi_iou_x
CLS_FG_THRESH: [0.75]
CLS_BG_THRESH: [0.25]
CLS_BG_THRESH_LO: 0.1
HARD_BG_RATIO: 0.8
REG_FG_THRESH: [0.5]
ENABLE_HARD_SAMPLING: False
HARD_SAMPLING_THRESH: [0.5]
HARD_SAMPLING_RATIO: [0.5]
STAGE1:
ROI_PER_IMAGE: 160
FG_RATIO: 0.5
SAMPLE_ROI_BY_EACH_CLASS: True
CLS_SCORE_TYPE: roi_iou_x
CLS_FG_THRESH: [0.75]
CLS_BG_THRESH: [0.25]
CLS_BG_THRESH_LO: 0.1
HARD_BG_RATIO: 0.8
REG_FG_THRESH: [0.55]
ENABLE_HARD_SAMPLING: True
HARD_SAMPLING_THRESH: [0.5]
HARD_SAMPLING_RATIO: [0.5]
STAGE2:
ROI_PER_IMAGE: 160
FG_RATIO: 0.5
SAMPLE_ROI_BY_EACH_CLASS: True
CLS_SCORE_TYPE: roi_iou_x
CLS_FG_THRESH: [0.75]
CLS_BG_THRESH: [0.25]
CLS_BG_THRESH_LO: 0.1
HARD_BG_RATIO: 0.8
REG_FG_THRESH: [0.6]
ENABLE_HARD_SAMPLING: True
HARD_SAMPLING_THRESH: [0.5]
HARD_SAMPLING_RATIO: [0.5]
LOSS_CONFIG:
CLS_LOSS: BinaryCrossEntropy
REG_LOSS: smooth-l1
CORNER_LOSS_REGULARIZATION: True
GRID_3D_IOU_LOSS: False
LOSS_WEIGHTS: {
'rcnn_cls_weight': 1.0,
'rcnn_reg_weight': 1.0,
'rcnn_corner_weight': 1.0,
'rcnn_iou3d_weight': 1.0,
'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
}
POST_PROCESSING:
RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
SCORE_THRESH: 0.4
OUTPUT_RAW_SCORE: False
EVAL_METRIC: kitti
IoU: 0.9
RL: True
NMS_CONFIG:
MULTI_CLASSES_NMS: False
NMS_TYPE: nms_gpu
NMS_THRESH: 0.1
NMS_PRE_MAXSIZE: 4096
NMS_POST_MAXSIZE: 500
OPTIMIZATION:
BATCH_SIZE_PER_GPU: 2
NUM_EPOCHS: 60
OPTIMIZER: adam_onecycle
LR: 0.01
WEIGHT_DECAY: 0.01
MOMENTUM: 0.9
MOMS: [0.95, 0.85]
PCT_START: 0.4
DIV_FACTOR: 10
DECAY_STEP_LIST: [35, 45]
LR_DECAY: 0.1
LR_CLIP: 0.0000001
LR_WARMUP: False
WARMUP_EPOCH: 1
GRAD_NORM_CLIP: 10