Hugging Face's logo

microsoft
/
rad-dino

Image Feature Extraction
Transformers
Safetensors
dinov2
Model card Files
xet
Community
11
rad-dino
File size: 3,192 Bytes 
428e563
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
MODEL:
  WEIGHTS: ''
compute_precision:
  grad_scaler: true
  teacher:
    backbone:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp16
        buffer_dtype: fp32
    dino_head:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp16
        buffer_dtype: fp32
    ibot_head:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp16
        buffer_dtype: fp32
  student:
    backbone:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp16
        buffer_dtype: fp32
    dino_head:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp32
        buffer_dtype: fp32
    ibot_head:
      sharding_strategy: SHARD_GRAD_OP
      mixed_precision:
        param_dtype: fp16
        reduce_dtype: fp32
        buffer_dtype: fp32
dino:
  loss_weight: 1.0
  head_n_prototypes: 65536
  head_bottleneck_dim: 256
  head_nlayers: 3
  head_hidden_dim: 2048
  koleo_loss_weight: 0.1
ibot:
  loss_weight: 1.0
  mask_sample_probability: 0.5
  mask_ratio_min_max:
  - 0.1
  - 0.5
  separate_head: false
  head_n_prototypes: 65536
  head_bottleneck_dim: 256
  head_nlayers: 3
  head_hidden_dim: 2048
train:
  batch_size_per_gpu: 64
  dataset_path: ImageNet:split=TRAIN
  output_dir: .
  saveckp_every_n_epoch: 5
  seed: 0
  num_workers: 10
  OFFICIAL_EPOCH_LENGTH: 0 # automatic rescaling based on the dataset len is applied if this is set to 0
  cache_dataset: true
  centering: "centering" # or "sinkhorn_knopp"
student:
  arch: vit_large
  patch_size: 16
  drop_block_rate: 0.0
  drop_path_rate: 0.3
  layerscale: 1.0e-05
  drop_path_uniform: true
  pretrained_weights: ''
  ffn_layer: "mlp"
  block_chunks: 0
  qkv_bias: true
  proj_bias: true
  ffn_bias: true
  num_register_tokens: 0
  interpolate_antialias: false
  interpolate_offset: 0.1
  load_weights: true
  checkpoints_dir: null
teacher:
  momentum_teacher: 0.992
  final_momentum_teacher: 1
  warmup_teacher_temp: 0.04
  teacher_temp: 0.07
  warmup_teacher_temp_epochs: 30
optim:
  epochs: 100
  weight_decay: 0.04
  weight_decay_end: 0.4
  base_lr: 0.004  # learning rate for a batch size of 1024
  lr: 0.  # will be set after applying scaling rule
  warmup_epochs: 10
  min_lr: 1.0e-06
  clip_grad: 3.0
  freeze_last_layer_epochs: 1
  scaling_rule: sqrt_wrt_1024
  patch_embed_lr_mult: 0.2
  layerwise_decay: 0.9
  adamw_beta1: 0.9
  adamw_beta2: 0.999
crops:
  global_crops_scale:
  - 0.32
  - 1.0
  local_crops_number: 8
  local_crops_scale:
  - 0.05
  - 0.32
  global_crops_size: 224
  local_crops_size: 96
evaluation:
  eval_period_iterations: 12500
  dataset_str: None
  online:  # see dinov2.eval.linear_callback for documentation
    learning_rate: 1e-6  # will be multiplied by batch size and number of devices
    num_last_blocks: 1
    add_avg_pool: true
    num_update_epochs_per_eval: 3
    augmentation:
      degrees: 30
      scale:
      - 0.8
      - 1.2
      shear: 15
      interpolation: BICUBIC
      horizontal_flip: true