| { |
| "module": "keras_hub.src.models.sam3.sam3_pc_backbone", |
| "class_name": "SAM3PromptableConceptBackbone", |
| "config": { |
| "name": "sam3_promptable_concept_backbone", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "vision_encoder": { |
| "module": "keras_hub.src.models.sam3.sam3_vision_encoder", |
| "class_name": "SAM3VisionEncoder", |
| "config": { |
| "name": "sam3_vision_encoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "image_shape": [ |
| 1008, |
| 1008, |
| 3 |
| ], |
| "patch_size": 14, |
| "num_layers": 32, |
| "hidden_dim": 1024, |
| "intermediate_dim": 4736, |
| "num_heads": 16, |
| "fpn_hidden_dim": 256, |
| "fpn_scale_factors": [ |
| 4.0, |
| 2.0, |
| 1.0, |
| 0.5 |
| ], |
| "pretrain_image_shape": [ |
| 336, |
| 336, |
| 3 |
| ], |
| "hidden_activation": "gelu", |
| "rope_theta": 10000.0, |
| "window_size": 24, |
| "global_attn_indexes": [ |
| 7, |
| 15, |
| 23, |
| 31 |
| ], |
| "attention_dropout_rate": 0.0, |
| "hidden_dropout_rate": 0.0, |
| "layer_norm_epsilon": 1e-06 |
| }, |
| "registered_name": "keras_hub>SAM3VisionEncoder" |
| }, |
| "text_encoder": { |
| "module": "keras_hub.src.models.sam3.sam3_text_encoder", |
| "class_name": "SAM3TextEncoder", |
| "config": { |
| "name": "sam3_text_encoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "vocabulary_size": 49408, |
| "embedding_dim": 1024, |
| "hidden_dim": 1024, |
| "num_layers": 24, |
| "num_heads": 16, |
| "intermediate_dim": 4096, |
| "intermediate_activation": "gelu", |
| "max_sequence_length": 32, |
| "layer_norm_epsilon": 1e-05 |
| }, |
| "registered_name": "keras_hub>SAM3TextEncoder" |
| }, |
| "geometry_encoder": { |
| "module": "keras_hub.src.models.sam3.sam3_geometry_encoder", |
| "class_name": "SAM3GeometryEncoder", |
| "config": { |
| "name": "sam3_geometry_encoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "num_layers": 3, |
| "hidden_dim": 256, |
| "intermediate_dim": 2048, |
| "num_heads": 8, |
| "roi_size": 7, |
| "hidden_activation": "relu", |
| "dropout_rate": 0.0, |
| "layer_norm_epsilon": 1e-06 |
| }, |
| "registered_name": "keras_hub>SAM3GeometryEncoder" |
| }, |
| "detr_encoder": { |
| "module": "keras_hub.src.models.sam3.sam3_detr_encoder", |
| "class_name": "SAM3DetrEncoder", |
| "config": { |
| "name": "sam3_detr_encoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "num_layers": 6, |
| "hidden_dim": 256, |
| "intermediate_dim": 2048, |
| "num_heads": 8, |
| "hidden_activation": "relu", |
| "dropout_rate": 0.1, |
| "layer_norm_epsilon": 1e-06 |
| }, |
| "registered_name": "keras_hub>SAM3DetrEncoder" |
| }, |
| "detr_decoder": { |
| "module": "keras_hub.src.models.sam3.sam3_detr_decoder", |
| "class_name": "SAM3DetrDecoder", |
| "config": { |
| "name": "sam3_detr_decoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "image_shape": [ |
| 1008, |
| 1008, |
| 3 |
| ], |
| "patch_size": 14, |
| "num_layers": 6, |
| "hidden_dim": 256, |
| "intermediate_dim": 2048, |
| "num_heads": 8, |
| "num_queries": 200, |
| "hidden_activation": "relu", |
| "dropout_rate": 0.1, |
| "layer_norm_epsilon": 1e-06 |
| }, |
| "registered_name": "keras_hub>SAM3DetrDecoder" |
| }, |
| "mask_decoder": { |
| "module": "keras_hub.src.models.sam3.sam3_mask_decoder", |
| "class_name": "SAM3MaskDecoder", |
| "config": { |
| "name": "sam3_mask_decoder", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "num_upsampling_stages": 3, |
| "hidden_dim": 256, |
| "num_heads": 8, |
| "dropout_rate": 0.0, |
| "layer_norm_epsilon": 1e-06 |
| }, |
| "registered_name": "keras_hub>SAM3MaskDecoder" |
| } |
| }, |
| "registered_name": "keras_hub>SAM3PromptableConceptBackbone" |
| } |