-
Notifications
You must be signed in to change notification settings - Fork 11
/
Copy pathcp-pillar-v0.4_sparsekd.yaml
333 lines (278 loc) · 8.78 KB
/
cp-pillar-v0.4_sparsekd.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
CLASS_NAMES: ['Vehicle', 'Pedestrian', 'Cyclist']
TEACHER_CKPT: '../output/model_zoo/cp-pillar/cp-pillar_5909.pth'
PRETRAINED_MODEL: '../output/model_zoo/cp-pillar/cp-pillar_5909.pth'
DATA_CONFIG:
_BASE_CONFIG_: cfgs/dataset_configs/waymo_dataset.yaml
POINT_CLOUD_RANGE: [-73.6, -73.6, -2, 73.6, 73.6, 4.0]
DATA_PROCESSOR:
- NAME: mask_points_and_boxes_outside_range
REMOVE_OUTSIDE_BOXES: True
- NAME: shuffle_points
SHUFFLE_ENABLED: {
'train': True,
'test': True
}
- NAME: transform_points_to_voxels
VOXEL_SIZE: [ 0.4, 0.4, 6.0 ]
MAX_POINTS_PER_VOXEL: 28
MAX_NUMBER_OF_VOXELS: {
'train': 150000,
'test': 150000
}
- NAME: transform_points_to_voxels_tea
VOXEL_SIZE: [ 0.32, 0.32, 6.0 ]
MAX_POINTS_PER_VOXEL: 20
MAX_NUMBER_OF_VOXELS: {
'train': 150000,
'test': 150000
}
MODEL:
NAME: CenterPoint
VFE:
NAME: PillarVFE
WITH_DISTANCE: False
USE_ABSLOTE_XYZ: True
USE_NORM: True
NUM_FILTERS: [ 64, 64 ]
MAP_TO_BEV:
NAME: PointPillarScatter
NUM_BEV_FEATURES: 64
BACKBONE_2D:
NAME: BaseBEVBackbone
WIDTH: 1.0
LAYER_NUMS: [ 3, 5, 5 ]
LAYER_STRIDES: [ 1, 2, 2 ]
NUM_FILTERS: [ 64, 128, 256 ]
UPSAMPLE_STRIDES: [ 1, 2, 4 ]
NUM_UPSAMPLE_FILTERS: [ 128, 128, 128 ]
FOCUS: False
ACT_FN: ReLU
DENSE_HEAD:
NAME: CenterHead
CLASS_AGNOSTIC: False
CLASS_NAMES_EACH_HEAD: [
['Vehicle', 'Pedestrian', 'Cyclist']
]
SHARED_CONV_CHANNEL: 64
USE_BIAS_BEFORE_NORM: True
NUM_HM_CONV: 2
SEPARATE_HEAD_CFG:
HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']
HEAD_DICT: {
'center': {'out_channels': 2, 'num_conv': 2},
'center_z': {'out_channels': 1, 'num_conv': 2},
'dim': {'out_channels': 3, 'num_conv': 2},
'rot': {'out_channels': 2, 'num_conv': 2},
}
TARGET_ASSIGNER_CONFIG:
FEATURE_MAP_STRIDE: 1
NUM_MAX_OBJS: 500
GAUSSIAN_OVERLAP: 0.1
MIN_RADIUS: 2
SHARPER: False
LOSS_CONFIG:
LOSS_WEIGHTS: {
'cls_weight': 1.0,
'loc_weight': 2.0,
'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
}
POST_PROCESSING:
SCORE_THRESH: 0.1
POST_CENTER_LIMIT_RANGE: [-80, -80, -10.0, 80, 80, 10.0]
MAX_OBJ_PER_SAMPLE: 500
NMS_CONFIG:
NMS_TYPE: nms_gpu
NMS_THRESH: 0.7
NMS_PRE_MAXSIZE: 4096
NMS_POST_MAXSIZE: 500
POST_PROCESSING:
RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
EVAL_METRIC: waymo
EVAL_CLASSES: {
'LEVEL_2/AP': [ 'OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/AP',
'OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/AP',
'OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/AP'
],
'LEVEL_2/APH': [ 'OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/APH',
'OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/APH',
'OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/APH'
]
}
MODEL_TEACHER:
NAME: CenterPoint
IS_TEACHER: True
VFE:
NAME: PillarVFE
WITH_DISTANCE: False
USE_ABSLOTE_XYZ: True
USE_NORM: True
NUM_FILTERS: [ 64, 64 ]
MAP_TO_BEV:
NAME: PointPillarScatter
NUM_BEV_FEATURES: 64
BACKBONE_2D:
NAME: BaseBEVBackbone
LAYER_NUMS: [ 3, 5, 5 ]
LAYER_STRIDES: [ 1, 2, 2 ]
NUM_FILTERS: [ 64, 128, 256 ]
UPSAMPLE_STRIDES: [ 1, 2, 4 ]
NUM_UPSAMPLE_FILTERS: [ 128, 128, 128 ]
FOCUS: False
ACT_FN: ReLU
DENSE_HEAD:
NAME: CenterHead
CLASS_AGNOSTIC: False
CLASS_NAMES_EACH_HEAD: [
['Vehicle', 'Pedestrian', 'Cyclist']
]
SHARED_CONV_CHANNEL: 64
USE_BIAS_BEFORE_NORM: True
NUM_HM_CONV: 2
SEPARATE_HEAD_CFG:
HEAD_ORDER: ['center', 'center_z', 'dim', 'rot']
HEAD_DICT: {
'center': {'out_channels': 2, 'num_conv': 2},
'center_z': {'out_channels': 1, 'num_conv': 2},
'dim': {'out_channels': 3, 'num_conv': 2},
'rot': {'out_channels': 2, 'num_conv': 2},
}
TARGET_ASSIGNER_CONFIG:
FEATURE_MAP_STRIDE: 1
NUM_MAX_OBJS: 500
GAUSSIAN_OVERLAP: 0.1
MIN_RADIUS: 2
SHARPER: False
LOSS_CONFIG:
LOSS_WEIGHTS: {
'cls_weight': 1.0,
'loc_weight': 2.0,
'code_weights': [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
}
POST_PROCESSING:
SCORE_THRESH: 0.1
POST_CENTER_LIMIT_RANGE: [-80, -80, -10.0, 80, 80, 10.0]
MAX_OBJ_PER_SAMPLE: 500
NMS_CONFIG:
NMS_TYPE: nms_gpu
NMS_THRESH: 0.7
NMS_PRE_MAXSIZE: 4096
NMS_POST_MAXSIZE: 500
POST_PROCESSING:
RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
EVAL_METRIC: waymo
EVAL_CLASSES: {
'LEVEL_2/AP': [ 'OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/AP',
'OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/AP',
'OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/AP'
],
'LEVEL_2/APH': [ 'OBJECT_TYPE_TYPE_VEHICLE_LEVEL_2/APH',
'OBJECT_TYPE_TYPE_PEDESTRIAN_LEVEL_2/APH',
'OBJECT_TYPE_TYPE_CYCLIST_LEVEL_2/APH'
]
}
OPTIMIZATION:
BATCH_SIZE_PER_GPU: 2
NUM_EPOCHS: 30
OPTIMIZER: adam_onecycle
LR: 0.003
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
REMAP_PRETRAIN:
ENABLED: False
WAY: BN_SCALE
BN_SCALE:
ABS: True
OFA:
l1_norm: max
KD:
ENABLED: True
TEACHER_MODE: train # train or eval
DIFF_VOXEL: True # use different voxel size between teacher and student
MASK:
SCORE_MASK: False
FG_MASK: False
BOX_MASK: False
LOGIT_KD:
ENABLED: True
# decode prediction to bounding boxes or not in logit kd
MODE: raw_pred # [raw_pred, decoded_boxes, target]
ALIGN: {
MODE: interpolate,
target: teacher,
mode: bilinear, # nearest, linear, bilinear, bicubic, trilinear, area
align_corners: True,
align_channel: False
}
FEATURE_KD:
ENABLED: False
FEATURE_NAME: spatial_features_2d
FEATURE_NAME_TEA: spatial_features_2d
# Align feature map
ALIGN: {
ENABLED: False,
MODE: interpolate,
target: teacher,
# interpolate params
mode: bilinear, # nearest, linear, bilinear, bicubic, trilinear, area
align_corners: True,
align_channel: False,
# conv params
num_filters: [ 192, 384 ], # [in_channel, out_channel]
use_norm: True,
use_act: False,
kernel_size: 3,
groups: 1,
}
ROI_POOL:
ENABLED: True
GRID_SIZE: 7
DOWNSAMPLE_RATIO: 1
ROI: gt # ['gt', 'tea', 'stu']
THRESH: 0.0 # for teacher prediction for student prediction
LABEL_ASSIGN_KD:
ENABLED: True
SCORE_TYPE: cls
USE_GT: True
GT_FIRST: False # when concatenate the gt boxes and target predictions,
# target boxes selection
SCORE_THRESH: [ 0.6, 0.6, 0.6 ]
NMS_CONFIG:
ENABLED: False
NMS_TYPE: nms_gpu
NMS_THRESH: 0.7
NMS_PRE_MAXSIZE: 4096
NMS_POST_MAXSIZE: 500
KD_LOSS:
ENABLED: True
HM_LOSS: {
type: MSELoss,
weight: 7.0,
thresh: 0.0, # threshold for score PP Logit KD
fg_mask: True,
soft_mask: True,
rank: -1, # rank PP Logit KD, -1 means not used
}
REG_LOSS: {
type: RegLossCenterNet,
# for L1 loss only
code_weights: [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0],
weight: 0.0
}
FEATURE_LOSS: {
mode: rois,
type: MSELoss, # [SmoothL1Loss, MSELoss]
weight: 0.1,
# weight mask
fg_mask: False,
score_mask: False,
score_thresh: 0.3
}