This is a DINOV3 model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. Model config:

  • name: dinov3_backbone
  • trainable: True
  • dtype: {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
  • patch_size: 16
  • num_layers: 24
  • hidden_dim: 1024
  • num_heads: 16
  • intermediate_dim: 4096
  • num_register_tokens: 4
  • use_mask_token: True
  • layer_scale_init_value: 1.0
  • hidden_activation: gelu
  • use_gated_mlp: False
  • use_query_bias: True
  • use_key_bias: False
  • use_value_bias: True
  • use_proj_bias: True
  • use_mlp_bias: True
  • attention_dropout: 0.0
  • drop_path_rate: 0.0
  • layer_norm_eps: 1e-05
  • image_shape: [224, 224, 3]
  • rope_theta: 100.0
  • apply_layernorm: False

This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.

Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support