keras/depth_anything_v2_small

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

• name: depth_anything_backbone
• trainable: True
• dtype: {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
• image_encoder: {'module': 'keras_hub.src.models.dinov2.dinov2_backbone', 'class_name': 'DINOV2Backbone', 'config': {'name': 'dinov2_backbone', 'trainable': True, 'dtype': {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}, 'patch_size': 14, 'num_layers': 12, 'hidden_dim': 384, 'num_heads': 6, 'intermediate_dim': 1536, 'layer_scale_init_value': 1.0, 'num_register_tokens': 0, 'use_mask_token': True, 'use_swiglu_ffn': False, 'dropout_rate': 0.0, 'drop_path_rate': 0.0, 'image_shape': [518, 518, 3], 'position_embedding_shape': [518, 518], 'antialias_in_interpolation': False, 'apply_layernorm': True}, 'registered_name': 'keras_hub>DINOV2Backbone'}
• reassemble_factors: [4, 2, 1, 0.5]
• neck_hidden_dims: [48, 96, 192, 384]
• fusion_hidden_dim: 64
• head_hidden_dim: 32
• head_in_index: -1
• feature_keys: ['stage3', 'stage6', 'stage9', 'stage12']

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