Keras
Keras 3 API documentation
KerasHub
Pretrained Models
Segment Anything Model
SAMBackbone model

SAMBackbone model

source

SAMBackbone class 

keras_hub.models.SAMBackbone(
    image_encoder, prompt_encoder, mask_decoder, dtype=None, **kwargs
)

A backbone for the Segment Anything Model (SAM).

Arguments

Example

image_size=128
batch_size=2
input_data = {
    "images": np.ones(
        (batch_size, image_size, image_size, 3),
        dtype="float32",
    ),
    "points": np.ones((batch_size, 1, 2), dtype="float32"),
    "labels": np.ones((batch_size, 1), dtype="float32"),
    "boxes": np.ones((batch_size, 1, 2, 2), dtype="float32"),
    "masks": np.zeros(
        (batch_size, 0, image_size, image_size, 1)
    ),
}
image_encoder = keras_hub.models.ViTDetBackbone(
    hidden_size=16,
    num_layers=16,
    intermediate_dim=16 * 4,
    num_heads=16,
    global_attention_layer_indices=[2, 5, 8, 11],
    patch_size=16,
    num_output_channels=8,
    window_size=2,
    image_shape=(image_size, image_size, 3),
)
prompt_encoder = keras_hub.layers.SAMPromptEncoder(
    hidden_size=8,
    image_embedding_size=(8, 8),
    input_image_size=(
        image_size,
        image_size,
    ),
    mask_in_channels=16,
)
mask_decoder = keras_hub.layers.SAMMaskDecoder(
    num_layers=2,
    hidden_size=8,
    intermediate_dim=32,
    num_heads=8,
    embedding_dim=8,
    num_multimask_outputs=3,
    iou_head_depth=3,
    iou_head_hidden_dim=8,
)
backbone = keras_hub.models.SAMBackbone(
    image_encoder=image_encoder,
    prompt_encoder=prompt_encoder,
    mask_decoder=mask_decoder,
    image_shape=(image_size, image_size, 3),
)
backbone(input_data)

source

from_preset method 

SAMBackbone.from_preset(preset, load_weights=True, **kwargs)

Instantiate a keras_hub.models.Backbone from a model preset.

A preset is a directory of configs, weights and other file assets used to save and load a pre-trained model. The preset can be passed as a one of:

  1. a built-in preset identifier like 'bert_base_en'
  2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
  3. a Hugging Face handle like 'hf://user/bert_base_en'
  4. a path to a local preset directory like './bert_base_en'

This constructor can be called in one of two ways. Either from the base class like keras_hub.models.Backbone.from_preset(), or from a model class like keras_hub.models.GemmaBackbone.from_preset(). If calling from the base class, the subclass of the returning object will be inferred from the config in the preset directory.

For any Backbone subclass, you can run cls.presets.keys() to list all built-in presets available on the class.

Arguments

  • preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
  • load_weights: bool. If True, the weights will be loaded into the model architecture. If False, the weights will be randomly initialized.

Examples

# Load a Gemma backbone with pre-trained weights.
model = keras_hub.models.Backbone.from_preset(
    "gemma_2b_en",
)
# Load a Bert backbone with a pre-trained config and random weights.
model = keras_hub.models.Backbone.from_preset(
    "bert_base_en",
    load_weights=False,
)
Preset nameParametersDescription
sam_base_sa1b93.74MThe base SAM model trained on the SA1B dataset.
sam_large_sa1b641.09MThe large SAM model trained on the SA1B dataset.
sam_huge_sa1b312.34MThe huge SAM model trained on the SA1B dataset.