greatwall1
/
eye_camera
Not watched
1
0
Fork 0
Code
Releases 0 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
Tree: e0a114361e
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'e0a114361e'
${ noResults }
eye_camera/networks/vit_seg_configs.py

131 lines
4.3 kB
Raw Blame History 

  1. import ml_collections

  2. 

  3. def get_b16_config():

  4.     """Returns the ViT-B/16 configuration."""

  5.     config = ml_collections.ConfigDict()

  6.     config.patches = ml_collections.ConfigDict({'size': (16, 16)})

  7.     config.hidden_size = 768

  8.     config.transformer = ml_collections.ConfigDict()

  9.     config.transformer.mlp_dim = 3072

  10.     config.transformer.num_heads = 12

  11.     config.transformer.num_layers = 12

  12.     config.transformer.attention_dropout_rate = 0.0

  13.     config.transformer.dropout_rate = 0.1

  14. 

  15.     config.classifier = 'seg'

  16.     config.representation_size = None

  17.     config.resnet_pretrained_path = None

  18.     config.pretrained_path = '../model/vit_checkpoint/imagenet21k/ViT-B_16.npz'

  19.     config.patch_size = 16

  20. 

  21.     config.decoder_channels = (256, 128, 64, 16)

  22.     config.n_classes = 2

  23.     config.activation = 'softmax'

  24.     return config

  25. 

  26. 

  27. def get_testing():

  28.     """Returns a minimal configuration for testing."""

  29.     config = ml_collections.ConfigDict()

  30.     config.patches = ml_collections.ConfigDict({'size': (16, 16)})

  31.     config.hidden_size = 1

  32.     config.transformer = ml_collections.ConfigDict()

  33.     config.transformer.mlp_dim = 1

  34.     config.transformer.num_heads = 1

  35.     config.transformer.num_layers = 1

  36.     config.transformer.attention_dropout_rate = 0.0

  37.     config.transformer.dropout_rate = 0.1

  38.     config.classifier = 'token'

  39.     config.representation_size = None

  40.     return config

  41. 

  42. def get_r50_b16_config():

  43.     """Returns the Resnet50 + ViT-B/16 configuration."""

  44.     config = get_b16_config()

  45.     config.patches.grid = (16, 16)

  46.     config.resnet = ml_collections.ConfigDict()

  47.     config.resnet.num_layers = (3, 4, 9)

  48.     config.resnet.width_factor = 1

  49. 

  50.     config.classifier = 'seg'

  51.     config.pretrained_path = '../model/vit_checkpoint/imagenet21k/R50+ViT-B_16.npz'

  52.     config.decoder_channels = (256, 128, 64, 16)

  53.     config.skip_channels = [512, 256, 64, 16]

  54.     config.n_classes = 2

  55.     config.n_skip = 3

  56.     config.activation = 'softmax'

  57. 

  58.     return config

  59. 

  60. 

  61. def get_b32_config():

  62.     """Returns the ViT-B/32 configuration."""

  63.     config = get_b16_config()

  64.     config.patches.size = (32, 32)

  65.     config.pretrained_path = '../model/vit_checkpoint/imagenet21k/ViT-B_32.npz'

  66.     return config

  67. 

  68. 

  69. def get_l16_config():

  70.     """Returns the ViT-L/16 configuration."""

  71.     config = ml_collections.ConfigDict()

  72.     config.patches = ml_collections.ConfigDict({'size': (16, 16)})

  73.     config.hidden_size = 1024

  74.     config.transformer = ml_collections.ConfigDict()

  75.     config.transformer.mlp_dim = 4096

  76.     config.transformer.num_heads = 16

  77.     config.transformer.num_layers = 24

  78.     config.transformer.attention_dropout_rate = 0.0

  79.     config.transformer.dropout_rate = 0.1

  80.     config.representation_size = None

  81. 

  82.     # custom

  83.     config.classifier = 'seg'

  84.     config.resnet_pretrained_path = None

  85.     config.pretrained_path = '../model/vit_checkpoint/imagenet21k/ViT-L_16.npz'

  86.     config.decoder_channels = (256, 128, 64, 16)

  87.     config.n_classes = 2

  88.     config.activation = 'softmax'

  89.     return config

  90. 

  91. 

  92. def get_r50_l16_config():

  93.     """Returns the Resnet50 + ViT-L/16 configuration. customized """

  94.     config = get_l16_config()

  95.     config.patches.grid = (16, 16)

  96.     config.resnet = ml_collections.ConfigDict()

  97.     config.resnet.num_layers = (3, 4, 9)

  98.     config.resnet.width_factor = 1

  99. 

  100.     config.classifier = 'seg'

  101.     config.resnet_pretrained_path = '../model/vit_checkpoint/imagenet21k/R50+ViT-B_16.npz'

  102.     config.decoder_channels = (256, 128, 64, 16)

  103.     config.skip_channels = [512, 256, 64, 16]

  104.     config.n_classes = 2

  105.     config.activation = 'softmax'

  106.     return config

  107. 

  108. 

  109. def get_l32_config():

  110.     """Returns the ViT-L/32 configuration."""

  111.     config = get_l16_config()

  112.     config.patches.size = (32, 32)

  113.     return config

  114. 

  115. 

  116. def get_h14_config():

  117.     """Returns the ViT-L/16 configuration."""

  118.     config = ml_collections.ConfigDict()

  119.     config.patches = ml_collections.ConfigDict({'size': (14, 14)})

  120.     config.hidden_size = 1280

  121.     config.transformer = ml_collections.ConfigDict()

  122.     config.transformer.mlp_dim = 5120

  123.     config.transformer.num_heads = 16

  124.     config.transformer.num_layers = 32

  125.     config.transformer.attention_dropout_rate = 0.0

  126.     config.transformer.dropout_rate = 0.1

  127.     config.classifier = 'token'

  128.     config.representation_size = None

  129. 

  130.     return config