DEIMv2/configs/deimv2/deimv2_dinov3_x_coco.yml at main · NikhilSandy/DEIMv2 · GitHub

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
__include__: [
  '../dataset/coco_detection.yml',
  '../runtime.yml',
  '../base/dataloader.yml',
  '../base/optimizer.yml',
  '../base/deimv2.yml',
]


output_dir: ./outputs/deimv2_dinov3_x_coco

DEIM:
  backbone: DINOv3STAs

DINOv3STAs:
  name: dinov3_vits16plus
  weights_path: ./ckpts/dinov3_vits16plus_pretrain_lvd1689m-4057cbaa.pth
  interaction_indexes: [5,8,11]   # only need the [1/8, 1/16, 1/32]
  finetune: True
  conv_inplane: 64
  hidden_dim: 256

HybridEncoder:
  in_channels: [256, 256, 256]
  # intra
  hidden_dim: 256
  dim_feedforward: 1024

  # cross
  expansion: 1.25
  depth_mult: 1.37

DEIMTransformer:
  num_layers: 6
  eval_idx: -1
  feat_channels: [256, 256, 256]
  # reg_scale: 8
  hidden_dim: 256
  dim_feedforward: 2048

optimizer:
  type: AdamW
  params:
    -
      # except norm/bn/bias in self.dinov3
      params: '^(?=.*.dinov3)(?!.*(?:norm|bn|bias)).*$'
      lr: 0.00001
    -
      # including norm/bn/bias in self.dinov3
      params: '^(?=.*.dinov3)(?=.*(?:norm|bn|bias)).*$'
      lr: 0.00001
      weight_decay: 0.
    -
      # including norm/bn/bias except for the self.dinov3
      params: '^(?=.*(?:sta|encoder|decoder))(?=.*(?:norm|bn|bias)).*$'
      weight_decay: 0.

  lr: 0.0005
  betas: [0.9, 0.999]
  weight_decay: 0.000125

## Dense O2O: Mosaic + Mixup + CopyBlend
train_dataloader:
  dataset:
    transforms:
      ops:
        - {type: Mosaic, output_size: 320, rotation_range: 10, translation_range: [0.1, 0.1], scaling_range: [0.5, 1.5],
           probability: 1.0, fill_value: 0, use_cache: True, max_cached_images: 50, random_pop: True}
        - {type: RandomPhotometricDistort, p: 0.5}
        - {type: RandomZoomOut, fill: 0}
        - {type: RandomIoUCrop, p: 0.8}
        - {type: SanitizeBoundingBoxes, min_size: 1}
        - {type: RandomHorizontalFlip}
        - {type: Resize, size: [640, 640], }
        - {type: SanitizeBoundingBoxes, min_size: 1}
        - {type: ConvertPILImage, dtype: 'float32', scale: True}
        - {type: Normalize, mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225]}
        - {type: ConvertBoxes, fmt: 'cxcywh', normalize: True}
      policy:
        epoch: [4, 29, 50]   # list

  collate_fn:
    mixup_epochs: [4, 29]
    stop_epoch: 50
    copyblend_epochs: [4, 50]
    base_size_repeat: 3

val_dataloader:
  dataset:
    transforms:
      ops:
        - {type: Resize, size: [640, 640], }
        - {type: ConvertPILImage, dtype: 'float32', scale: True}
        - {type: Normalize, mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225]}