Hugging Face's logo

InternScience
/
InternAgent

TensorBoard
qwen2_vl
Model card Files
xet
Metrics Community
InternAgent
File size: 3,205 Bytes 
62a2f1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
CLASS_NAMES: ['Car', 'Bus', 'Truck', 'Pedestrian', 'Cyclist']

DATA_CONFIG:
    _BASE_CONFIG_: cfgs/dataset_configs/once_dataset.yaml
    
    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: [0.1, 0.1, 0.2]
          MAX_POINTS_PER_VOXEL: 5
          MAX_NUMBER_OF_VOXELS: {
            'train': 60000,
            'test': 60000
          }
          COMPUTE_VOXEL_CENTERS: True

MODEL:
    NAME: SARA3D
    
    # Enable Adaptive Confidence Aggregation
    USE_ACA: True
    
    # ACA Configuration
    ACA_CONFIG:
        USE_DENSITY: True
        USE_CURVATURE: True
        USE_NORMALS: True
    
    VFE:
        NAME: RESAVFE
        USE_NORM: True
        USE_RESA: True
        WITH_DISTANCE: True
        NUM_FILTERS: [64, 64]

    BACKBONE_3D:
        NAME: VoxelResBackBone8x

    MAP_TO_BEV:
        NAME: HeightCompression
        NUM_BEV_FEATURES: 256

    BACKBONE_2D:
        NAME: BaseBEVBackbone

        LAYER_NUMS: [5, 5]
        LAYER_STRIDES: [1, 2]
        NUM_FILTERS: [128, 256]
        UPSAMPLE_STRIDES: [1, 2]
        NUM_UPSAMPLE_FILTERS: [256, 256]

    DENSE_HEAD:
        NAME: CenterHead
        CLASS_AGNOSTIC: False

        CLASS_NAMES_EACH_HEAD: [
            ['Car', 'Bus', 'Truck', '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: 8
            NUM_MAX_OBJS: 500
            GAUSSIAN_OVERLAP: 0.1
            MIN_RADIUS: 2
            DENSE_REG: 1

        LOSS_CONFIG:
            LOSS_WEIGHTS: {
                'cls_weight': 1.0,
                'loc_weight': 1.0,
                '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: [-75.2, -75.2, -5.0, 75.2, 75.2, 3.0]
            MAX_OBJ_PER_SAMPLE: 500
            NMS_CONFIG:
                MULTI_CLASSES_NMS: False
                NMS_TYPE: nms_gpu
                NMS_THRESH: 0.01
                NMS_PRE_MAXSIZE: 4096
                NMS_POST_MAXSIZE: 500
            

    POST_PROCESSING:
      RECALL_THRESH_LIST: [0.3, 0.5, 0.7]
      OUTPUT_RAW_SCORE: False
      EVAL_METRIC: once

OPTIMIZATION:
    BATCH_SIZE_PER_GPU: 4
    NUM_EPOCHS: 80

    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: 35