SAMBackbone 模型

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

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,
)
backbone(input_data)

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

# 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,
)