DEIMv2/configs/deimv2/deimv2_dinov3_s_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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
__include__: [
  '../dataset/coco_detection.yml',
  '../runtime.yml',
  '../base/dataloader.yml',
  '../base/optimizer.yml',
  '../base/deimv2.yml',
]

output_dir: ./outputs/deimv2_dinov3_s_coco

DEIM:
  backbone: DINOv3STAs

DINOv3STAs:
  name: vit_tiny
  embed_dim: 192
  weights_path: ./ckpts/vitt_distill.pt
  interaction_indexes: [3, 7, 11]   # only need the [1/8, 1/16, 1/32]
  num_heads: 3

HybridEncoder:
  in_channels: [192, 192, 192]
  depth_mult: 0.67
  expansion: 0.34
  hidden_dim: 192
  dim_feedforward: 512

DEIMTransformer:
  feat_channels: [192, 192, 192]
  hidden_dim: 192
  dim_feedforward: 512
  num_layers: 4  # 4 5 6
  eval_idx: -1  # -2 -3 -4


## Optimizer
optimizer:
  type: AdamW

  params:
    -
      # except norm/bn/bias in self.dinov3
      params: '^(?=.*.dinov3)(?!.*(?:norm|bn|bias)).*$'
      lr: 0.000025
    -
      # including all norm/bn/bias in self.dinov3
      params: '^(?=.*.dinov3)(?=.*(?:norm|bn|bias)).*$'
      lr: 0.000025
      weight_decay: 0.
    -
      # including all 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: 0.0001

# Increase to search for the optimal ema
epoches: 132 # 120 + 4n

## Our LR-Scheduler
flat_epoch: 64    # 4 + epoch // 2, e.g., 40 = 4 + 72 / 2
no_aug_epoch: 12

## Our DataAug
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, 64, 120]   # list

  collate_fn:
    base_size: 640
    mixup_prob: 0.5
    ema_restart_decay: 0.9999
    base_size_repeat: 20
    mixup_epochs: [4, 64]
    stop_epoch: 120
    copyblend_epochs: [4, 120]

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]}

DEIMCriterion:
  matcher:
    # change matcher
    change_matcher: True
    iou_order_alpha: 4.0
    matcher_change_epoch: 100